CN102460394A

CN102460394A - Systems and methods for a distributed hash table in a multi-core system

Info

Publication number: CN102460394A
Application number: CN2010800322607A
Authority: CN
Inventors: P·凯马尼; A·谢蒂; J·苏甘蒂
Original assignee: Citrix Systems Inc
Current assignee: Citrix Systems Inc
Priority date: 2009-06-22
Filing date: 2010-06-04
Publication date: 2012-05-16
Anticipated expiration: 2030-06-04
Also published as: US20100322250A1; EP2446359A1; US8737407B2; CA2766296A1; CN102460394B; CA2766296C; IL217122A0; US20140229600A1; US9621437B2; WO2011005394A2

Abstract

The present invention is directed towards systems and methods for using a distributed hash table to maintain the same configuration and resource persistency across a plurality of cores in a multi-core system. The distributed hash table includes a plurality of partitions, each partition being owned by a respective core of the multi-core system. A core may establish resources in the partition it owns. A core may request other cores to establish resources in the partitions they own and send resource information to the core. The core may locally cache the resource information.

Description

The system and method that is used for the distributed hashtable of multiple nucleus system

Related application

The application requires the right of priority of U.S. Patent application NO.12/489201; This U.S. Patent application title is " Systems and Methods for a Distributed Hash Table in a Multi-core System "; The applying date is on June 22nd, 2009, and this application all is contained in this by reference.

Technical field

The present invention relates generally to data communication network.Particularly, the present invention relates to use distributed hashtable to discern the system and method for the resource of the nuclear in the multiple nucleus system.

Background technology

In the single-processor system, a processor comprises the configuration that is used to keep resource continuous property.This processor receives all portfolios, makes the load balance decision-making, and the identification service is created session and kept this session.In multiple nucleus system, on all nuclears of this system, keep identical configuration and resource continuous property is challenging.

Summary of the invention

The application is to using the use of keeping Resources Sustainability and/or tracking assets on a plurality of nuclears of distributed hashtable in multiple nucleus system.Each endorses the copy that comprises distributed hashtable.Distributed hashtable can be divided into a plurality of subregions.Each subregion can be assigned to different nuclear, or have by different nuclear.Each subregion can be associated with one or more resources.Have subregion like fruit stone, then the packet processing engine on this nuclear can be set up resource in this subregion.If this nuclear does not have subregion, then this nuclear must ask owner's nuclear in subregion, to set up resource.Packet processing engine on owner's nuclear is set up this resource and resource information is sent to requestor's nuclear in the subregion of its distributed hashtable.Packet processing engine on requestor's nuclear is buffered in this resource information in the subregion of distributing to owner's nuclear in its Hash table.In addition, the packet processing engine on the nuclear can upgrade the resource in the subregion that this nuclear has, and packet processing engine can be asked and buffer memory to the renewal of the resource in the subregion that has by other nuclears.

On the one hand, this solution is to the method for keeping the resource information of the resource of being set up by a plurality of Packet engine via distributed table, carries out on the corresponding nuclear of each Packet engine in multiple nucleus system.This method comprises by multiple nucleus system sets up the table that comprises a plurality of subregions, and each subregion of said a plurality of subregions is assigned to the corresponding nuclear of a plurality of nuclears of multinuclear device.This method comprises that also the resource information of the resource that will be set up by first Packet engine by first Packet engine of first nuclear of a plurality of nuclears stores first subregion of these a plurality of subregions into, and will be stored into second subregion of these a plurality of subregions by the resource information that second nuclear is set up by second Packet engine of second nuclear of these a plurality of nuclears.This method also comprises the request that is received identification first resource by first Packet engine of first nuclear.This method also comprise by first nuclear first Packet engine confirm first resource be stored in the first subregion different partition areas in.

In each embodiment, this method can comprise by the multinuclear device and based on the quantity of the nuclear of this multinuclear device said partition table is divided into a plurality of subregions.In other embodiments, this method can comprise by first Packet engine and receives this request on the virtual server of resource continuous property being configured to provide.In more embodiment, this method can comprise by the Hash of first Packet engine generation to the transport layer link information of this request.In certain embodiments, this method can comprise by first Packet engine and confirms that based on this Hash first resource is not stored in first subregion.In many examples, this method can comprise that discerning first resource by first Packet engine based on this Hash is set up by second nuclear.In each embodiment, this method can comprise that first subregion of visiting said partition table by first Packet engine is to confirm whether first resource is stored in first subregion.In certain embodiments; This method can comprise second request that is received identification second resource by first Packet engine; Confirm that second resource is stored in first subregion and the virtual server on first nuclear has online state; And confirm that in response to this second request is offered this virtual server, and wherein first resource is first session and second resource is second session.In many examples, this method can comprise second request that is received identification second resource by first Packet engine, confirms that second resource should be stored in first subregion and is not present in first subregion, and confirms in response to this, creates second resource.In certain embodiments, this method can comprise being authorized to second by first nuclear send message, and this message request information is to create first resource on first nuclear.In other embodiments; This method can comprise by second Packet engine confirms to exist in second subregion of said partition table first resource; Identification is that the state of the selected service of first resource is online by second Packet engine, and the response that will discern this service sends to first Packet engine.In many examples; This method can comprise by second Packet engine to be confirmed in second of said partition table divides into groups, not have first resource, and confirms to create first resource, is that the first resource selection service and the response that will discern this service send to first nuclear in response to this.In each embodiment, this method can comprise by first stone grafting receive from second nuclear, to the response of said message, confirm that the state of first the above service of nuclear is online, and in first subregion copy of buffer memory first resource.

Aspect another, this solution is to the system that keeps the resource information of the resource of being set up by a plurality of Packet engine via distributed partition table, carries out on the corresponding nuclear of each Packet engine in multiple nucleus system.This system comprises the partition table of being set up by multiple nucleus system, and this partition table comprises a plurality of subregions, and each subregion is assigned to the corresponding nuclear of this multiple nucleus system.This system is also included within first nuclear of multiple nucleus system and goes up first Packet engine of carrying out; The information stores of the resource that it will be set up by first Packet engine to first subregion of this partition table, receive identification first resource request, confirm that first resource is not stored in first subregion, and second subregion of identification storage first resource.This system also comprises second Packet engine of second nuclear of multiple nucleus system, and the information stores of the resource that it will be set up by second Packet engine is to second subregion of this partition table.

In each embodiment, can partition table be divided into a plurality of subregions based on the quantity of the nuclear of multiple nucleus system.In many examples, first Packet engine receives this request being configured to provide on the virtual server of resource continuous property.In other embodiments, first Packet engine can generate the Hash to the transport layer link information of request.In certain embodiments, first Packet engine can confirm that first resource is not stored in first subregion based on this Hash.In many examples, first Packet engine can confirm that first resource is by the second nuclear foundation based on this Hash.In certain embodiments, addressable first subregion of first Packet engine is to confirm whether first resource is stored in first subregion.In more embodiment; First Packet engine can receive second request of identification second resource; And can confirm that second resource is stored in first subregion and the virtual server on first nuclear has online state, and can confirm second request is offered this virtual server in response to this.In each embodiment, first Packet engine can receive second request of identification second resource, confirms in first subregion, not exist second resource and second resource should be stored in first subregion, and confirms to create second resource in response to this.In certain embodiments, first endorses to authorize to second and send message, and this message request information is to create first resource on first nuclear.In many examples, second Packet engine can be confirmed in second subregion to have first resource, and the state of discern service related with first resource is online, and the response that will discern this service sends to first and examines.In certain embodiments, second Packet engine can confirm in second subregion, not exist first resource, in response to said definite establishment first resource, is the first resource selection service, and the response that will discern this service sends to first nuclear.In certain embodiments, first Packet engine can receive from second nuclear, to the response of said message, confirm that the state of the service related with first resource is online, and in first subregion copy of buffer memory first resource.

In accompanying drawing below and the description details of each embodiment of the present invention has been carried out detailed elaboration.

Description of drawings

Through with reference to following description taken together with the accompanying drawings, aforementioned and other purpose, aspect, feature and advantage of the present invention will more obviously and be easier to understand, wherein:

Figure 1A is the block diagram of the embodiment of the client computer network environment of passing through the device access server;

Figure 1B transmits the block diagram of computing environment to the embodiment of the environment of client computer through equipment from server;

Fig. 1 C transmits the block diagram of computing environment to another embodiment of the environment of client computer through equipment from server;

Fig. 1 D transmits the block diagram of computing environment to another embodiment of the environment of client computer through equipment from server;

Fig. 1 E is the block diagram of the embodiment of calculation element to 1H;

Fig. 2 A is the block diagram of embodiment that is used for the equipment of the communication between processing client and the server;

Fig. 2 B be used to optimize, the block diagram of another embodiment of the equipment of the communication between acceleration, load balance and routed customer machine and the server;

Fig. 3 is the block diagram that is used for the embodiment of the client computer through equipment and server communication;

Fig. 4 A is the block diagram of the embodiment of virtualized environment;

Fig. 4 B is the block diagram of another embodiment of virtualized environment;

Fig. 4 C is the block diagram of the embodiment of virtual equipment;

Fig. 5 A is a block diagram of in multiple nucleus system, realizing parallel method embodiment;

Fig. 5 B is to use the block diagram of the system embodiment of multiple nucleus system;

Fig. 5 C is the block diagram of the another embodiment of multiple nucleus system aspect;

Fig. 6 A is the block diagram of the embodiment of distributed hashtable;

Fig. 6 B describe to cross over the process flow diagram of step of embodiment that a plurality of nuclears in the multiple nucleus system are kept the method for resource continuous property;

Fig. 6 C describes through distributed hashtable to cross over the process flow diagram of step of embodiment that a plurality of nuclears in the multiple nucleus system are kept the method for session continuity;

Fig. 6 D describes through distributed hashtable to cross over the process flow diagram of step of another embodiment that a plurality of nuclears in the multiple nucleus system are kept the method for session continuity; And

Fig. 6 E describes through distributed hashtable to cross over the process flow diagram of step of another embodiment that a plurality of nuclears in the multiple nucleus system are kept the method for session continuity.

From the detailed description of setting forth below in conjunction with accompanying drawing, feature and advantage of the present invention will be more obvious, and wherein, same reference marker is in the knowledge elements corresponding of getting the bid in full.In the accompanying drawings, same Reference numeral ordinary representation identical, similar element on the similar and/or structure on the function.

Embodiment

In order to read the description of following various embodiment, the description of content maybe be useful separately in following part and they for instructions:

-A partly describes is of value to network environment and the computing environment of implementing embodiment described herein;

-B partly describes the specific embodiment that is used for computing environment is sent to long-distance user's system and method;

-C partly describes the specific embodiment of the system and method that is used to quicken the communication between the client-server;

-D partly describes and is used for using the embodiment that transfer control carries out virtualized system and method.

-E partly describes the embodiment of the system and method that is used to provide multicore architecture and environment;

-F partly describes the embodiment of the system and method for the resource on the nuclear that is used for using distributed hashtable to follow the tracks of multiple nucleus system.

A. Network and computing environment

Before the details of the embodiment of the system and method for discussion equipment and/or client computer, network and computing environment that discussion can be disposed these embodiment therein are helpful.Referring now to Figure 1A,, the embodiment of network environment has been described.Summarize; Network environment comprises (same total server 106 that is called via one or more network 104,104 ' (total be called network 104) and one or more server 106a-106n; Or remote machine 106) one or more client computer 102a-102n (same total be called local machine 102 or client computer 102) of communication.In certain embodiments, client computer 102 is communicated by letter with server 106 through equipment 200.

Though Figure 1A shows network 104 and network 104 ' between client computer 102 and server 106, client computer 102 can be positioned on the same network 104 with server 106.Network 104 and 104 ' can be the network or the networks of different type of same type.Network 104 and/or 104 ' can be for example company's Intranet of Local Area Network, Metropolitan Area Network (MAN) (MAN), perhaps for example the Internet or WWW of wide area network (WAN).In one embodiment, network 104 ' can be dedicated network and network 104 can be public network.In certain embodiments, network 104 ' can be private and network 104 ' can be public network.In yet another embodiment, network 104 and 104 ' can all be a private.In certain embodiments, client computer 102 can be arranged in the branch offices of incorporated business, connects through the WAN on the network 104 and communicates by letter with the server that is positioned at the company data center 106.

Network 104 and/or 104 ' can be the network of any kind and/or form, and can comprise any following network: point to point network, radio network; Wide area network, LAN, communication network; Data communication network, computer network, ATM (asynchronous transfer mode) network; SONET (Synchronous Optical Network) network, SDH (SDH) network, wireless network and cable network.In certain embodiments, network 104 can comprise Radio Link, such as infrared channel or Landsat band.Network 104 and/or 104 ' topology can be bus-type, star-like or ring network is topological.Network 104 and/or 104 ' and network topology can be for any such network or network topology well known to those of ordinary skill in the art, that can support operation described herein.

Shown in Figure 1A, equipment 200 is displayed between network 104 and 104 ', and equipment 200 also can be called as interface unit 200 or gateway 200.In certain embodiments, equipment 200 can be positioned on the network 104.For example, the branch offices of company can be in branch offices deployment facility 200.In other embodiments, equipment 200 can be positioned at network 104 ' on.For example, equipment 200 can be positioned at the data center of company.In yet another embodiment, a plurality of equipment 200 can be in network 104 deploy.In certain embodiments, a plurality of equipment 200 can be deployed on the network 104 '.In one embodiment, first equipment 200 is communicated by letter with second equipment 200 '.In other embodiments, equipment 200 can be and is positioned at client computer 102 same or heterogeneous networks 104, arbitrary client computer 102 of 104 ' or the part of server 106.One or more equipment 200 can be at network between client computer 102 and the server 106 or any point in the network communication path.

In certain embodiments, equipment 200 comprises any network equipment that is called as Citrix NetScaler equipment by the Citrix Systems manufactured that is positioned at Florida State Ft.Lauderdale.In other embodiments, equipment 200 comprises any one product embodiments that is called as WebAccelerator and BigIP by the F5 Networks manufactured that is positioned at Seattle, the State of Washington.In yet another embodiment, equipment 205 comprises by the DX acceleration equipment platform of the Juniper Networks manufactured that is arranged in California Sunnyvale and/or such as any one of the SSL VPN serial equipment of SA700, SA2000, SA4000 and SA6000.In yet another embodiment; Equipment 200 comprises any application is quickened and/or safety is relevant equipment and/or the software by the Cisco Systems manufactured that is positioned at California San Jose, for example Cisco ACE application controls engine modules service (Application Control Engine Module service) software and mixed-media network modules mixed-media and Cisco AVS serial application speed system (Application Velocity System).

In one embodiment, system can comprise the server 106 of a plurality of logic groups.In these embodiment, server logical divides into groups to be called as server zone 38.Therein among some embodiment, server 106 can be geographical going up to be disperseed.In some cases, crowd 38 can be used as single entity and is managed.In other embodiments, server zone 38 comprises a plurality of server zones 38.In one embodiment, on behalf of one or more client computer 102, server zone carry out one or more application programs.

Server 106 in each group 38 can be variety classes.One or more servers 106 can be according to one type operating system platform (for example; WINDOWS NT by the Microsoft manufactured of State of Washington Redmond) operation; And one or more other servers 106 can be according to operating system platform (for example, Unix or the Linux) operation of another type.The server 106 of each group 38 need be with physically not approaching with another server 106 in a group 38.Therefore, can be used wide area network (WAN) to connect by logic groups for 106 groups of crowd's servers of 38 or Metropolitan Area Network (MAN) (MAN) connects interconnected.For example, crowd 38 can comprise the server 106 in the zones of different, country, state, city, campus or the room that are physically located at different continents or continent.If use Local Area Network to connect or some direct-connected forms are come Connection Service device 106, then can increase the data transfer rate of 106 of servers among the crowd 38.

Server 106 can refer to file server, application server, web server, acting server or gateway server.In certain embodiments, server 106 can have as application server or as the ability of master application server work.In one embodiment, server 106 can comprise Active Directory.Client computer 102 also can be described as client node or end points.In certain embodiments, client computer 102 can have the ability of seeking the application on the access server as client node, and also can have as application server provides the ability to the visit of posting the application of carrying for other client computer 102a-102n.

In certain embodiments, client computer 102 is communicated by letter with server 106.In one embodiment, client computer 102 can with one of them direct communication of server 106 among the crowd 38.In yet another embodiment, client computer 102 executive routine proximity application (program neighborhood application) are to communicate by letter with crowd's 38 interior servers 106.In yet another embodiment, server 106 provides the function of host node.In certain embodiments, client computer 102 is communicated by letter with the server 106 among the crowd 38 through network 104.Through network 104, the server 106a-106n that client computer 102 for example can ask to carry out among the crowd 38 posts the various application of carrying, and the output of reception application execution result shows.In certain embodiments, have only host node identification to be provided and to provide and post the server 106 ' relevant required function of address information of carrying the application of being asked.

In one embodiment, server 106 provides the function of web server.In yet another embodiment, server 106a receives the request from client computer 102, and this request is forwarded to second server 106b, and uses from server 106b this request responding to be come the request of client computer 102 is responded.In yet another embodiment, server 106 obtain client computer 102 can with application enumerate and with by the relevant address information of the server of enumerating the application of being discerned of this application 106.In yet another embodiment, server 106 uses the web interface to offer client computer 102 to request responding.In one embodiment, the client computer 102 direct application of communicating by letter with server 106 and being discerned with visit.In yet another embodiment, client computer 102 receives the application output data such as video data that produces by carrying out the application of being discerned on the server 106.

With reference now to Figure 1B,, the embodiment of the network environment of disposing a plurality of equipment 200 has been described.First equipment 200 can be deployed on first network 104, and second equipment 200 ' be deployed in second network 104 ' on.For example, company can dispose first equipment 200 in branch offices, and data center dispose second equipment 200 '.In yet another embodiment, first equipment 200 and second equipment 200 ' be deployed on same network 104 or the network 104.For example, first equipment 200 can be used for first server zone 38 by deployment, and second equipment 200 can by deployment be used for second server crowd 38 '.In another example, first equipment 200 can be deployed in first branch offices, and second equipment 200 ' be deployed in second branch offices '.In certain embodiments, first equipment 200 and second equipment 200 ' collaborative each other or associated working is with the network traffic between the acceleration client-server or the transmission of application and data.

With reference now to Fig. 1 C,, another embodiment of network environment has been described, in this network environment, the deployed with devices of equipment 200 and one or more other types is in the same place, for example, be deployed in one or more WAN optimizing equipment 205,205 ' between.For example, a WAN optimizing equipment 205 be presented at network 104 and 104 ' between, and the 2nd WAN optimizing equipment 205 ' can be deployed between equipment 200 and the one or more server 106.For example, company can dispose a WAN optimizing equipment 205 in branch offices, and data center dispose the 2nd WAN optimizing equipment 205 '.In certain embodiments, equipment 205 can be positioned at network 104 ' on.In other embodiments, equipment 205 ' can be positioned on the network 104.In certain embodiments, equipment 205 ' can be positioned at network 104 ' or network 104 " on.In one embodiment, equipment 205 and 205 ' on same network.In yet another embodiment, equipment 205 and 205 ' on various network.In another example, a WAN optimizing equipment 205 can be used for first server zone 38 by deployment, and the 2nd WAN optimizing equipment 205 ' can by deployment be used for second server crowd 38 '.

In one embodiment, equipment 205 is devices of performance, operation or the service quality of the Network that is used to quicken, optimize or otherwise improve any kind and form (business of for example going to and/or being connected from WAN).In certain embodiments, equipment 205 is performance enhancement proxy.In other embodiments, equipment 205 is that the WAN of any kind and form optimizes or accelerator, also is called as the WAN optimal controller sometimes.In one embodiment, equipment 205 is any of the product embodiments that is called as WANScaler of being produced by the Citrix Systems company that is arranged in Florida State Ft.Lauderdale.In other embodiments, equipment 205 comprises any of the product embodiments that is called as BIG-IP link controller and WANjet of being produced by the F5 Networks company that is arranged in State of Washington Seattle.In yet another embodiment, equipment 205 comprises any of the WX that produced by the Juniper NetWorks company that is arranged in California Sunnyvale and WXC WAN accelerator platform.In certain embodiments, equipment 205 comprises any in the serial WAN optimizing equipment of rainbow trout (steelhead) of being produced by the Riverbed Technology company of California San Francisco.In other embodiments, equipment 205 comprises any of the WAN relevant apparatus of being produced by the Expand Networks company that is arranged in New Jersey Roseland.In one embodiment, equipment 205 comprises any WAN relevant device of being produced by the Packeteer company that is positioned at California Cupertino, the PacketShaper that is for example provided by Packeteer, iShared and SkyX product embodiments.In yet another embodiment; Equipment 205 comprises any WAN relevant device and/or the software of being produced by the Cisco Systems company that is positioned at California San Jose, for example Cisco wide area network application service software and mixed-media network modules mixed-media and wide area network engine apparatus.

In one embodiment, equipment 205 is that branch offices or telecottage provide application and data to quicken service.In one embodiment, equipment 205 comprises the optimization of wide area file service (WAFS).In yet another embodiment, equipment 205 quickens the transmission of file, for example via CIFS (CIFS) agreement.In other embodiments, equipment 205 provides high-speed cache to quicken to use the transmission with data in storer and/or memory storage.In one embodiment, equipment 205 is at the network stack of any rank or the compression of network traffic is provided in any agreement or network layer.In yet another embodiment, equipment 205 provides transport layer protocol optimization, flow control, performance to strengthen or revises and/or management, with the application in the acceleration WAN connection and the transmission of data.For example, in one embodiment, equipment 205 provides transmission control protocol (TCP) optimization.In other embodiments, equipment 205 provides optimization, flow control, performance for any session or application layer protocol to strengthen or modification and/or management.

In yet another embodiment, TCP customization or standard that equipment 205 is encoded into network packet with the data or the information of any kind and form and/or header fields or the Optional Field of IP, with it is existed, function or capability advertisement are given another equipment 205 '.In yet another embodiment, equipment 205 ' can use coded data in TCP and/or IP header fields or option is come and another equipment 205 ' communicate.For example, equipment can use tcp option or IP header fields or option pass on when carrying out the function of quickening such as WAN or for the work of combining with one another by equipment 205,205 ' employed one or more parameters.

In certain embodiments, equipment 200 be kept at equipment 205 and 205 ' between any information of encoding in the TCP that passes on and/or IP head and/or the Optional Field.For example, equipment 200 can stop connecting through the transport layer of equipment 200, for example through equipment 205 and 205 ' a transport layer between client-server connect.In one embodiment; Equipment 200 identification is also preserved by first equipment 205 and is connected any coded message in the transport layer packet of sending through first transport layer, and via second transport layer connect the transport layer packet that will have coded message be communicated to second equipment 205 '.

With reference now to Fig. 1 D,, the network environment that is used to transmit and/or operate the computing environment on the client computer 102 has been described.In certain embodiments, server 106 comprises the application transfer system 190 that is used for transmitting to one or more client computer 102 computing environment or application and/or data file.Generally speaking, client computer 10 is communicated by letter with server 106 with equipment 200 through network 104,104 '.For example, client computer 102 can reside in the telecottage of company, and for example branch offices, and server 106 can reside in the company data center.Client computer 102 comprises client proxy 120 and computing environment 15.The application that is used to visit, handle or use data file can be carried out or operated to computing environment 15.Can transmit computing environment 15, application and/or data file via equipment 200 and/or server 106.

In certain embodiments, equipment 200 speed-up computation environment 15 or its any part are to the transmission of client computer 102.In one embodiment, equipment 200 is through using the transmission of transfer system 190 speed-up computation environment 15.For example, can use embodiment described herein quicken from company's CSDC to the long-distance user position stream of (the for example branch offices of company) use (streaming application) and this uses the transmission of accessible data file.In yet another embodiment, the transport layer portfolio between equipment 200 acceleration client computer 102 and the server 106.Equipment 200 can be provided for quickening from server 106 to client computer the speed technology of any transport layer useful load of 102, for example: 1) transport layer connection pool, 2) transport layer connect multiplexed, 3) the transmission control protocol buffering, 4) compression and 5) high-speed cache.In certain embodiments, equipment 200 provides the load balance of server 106 in response to the request from client computer 102.In other embodiments, equipment 200 serve as agency or access server the visit to one or more server 106 is provided.In yet another embodiment, equipment 200 provides the secure virtual dedicated Internet access from first network 104 of client computer 102 to second network 104 ' of server 106, connects such as SSL VPN.In more another embodiment, equipment 200 provides the connection and application firewall safety, control and the management of communicating by letter between client computer 102 and the server 106.

In certain embodiments; Based on a plurality of manners of execution and based on through policy engine 195 applied arbitrary authentication vs. authorization strategies, use transfer management system 190 the application tranmission techniques that computing environment is sent to long-range or other user's desktop is provided.Use these technology, the long-distance user can obtain application and the data file that computing environment and access server are stored from any network connection device 100.In one embodiment, using transfer system 190 can reside on the server 106 or execution above that.In yet another embodiment, use transfer system 190 and can reside in the last or execution above that of a plurality of server 106a-106n.In certain embodiments, using transfer system 190 can carry out in server zone 38.In one embodiment, carry out the server 106 of using transfer system 190 and also can store or provide application and data file.In yet another embodiment, can carry out for first group of one or more servers 106 and use transfer system 190, and different server 106n can store or provide application and data file.In certain embodiments, using in transfer system 190, application and the data file each can be resident or be positioned at different servers.In yet another embodiment, using any part of transfer system 190 can be resident, carry out or be stored in or be distributed to equipment 200 or a plurality of equipment.

Client computer 102 can comprise being used to carry out to be used or the computing environment 15 of the application of deal with data file.Client computer 102 can through network 104,104 ' with application and the data file of equipment 200 requests from server 106.In one embodiment, equipment 200 can be forwarded to the request from client computer 102 server 106.For example, client computer 102 possibly not have local storage or local addressable application and data file.In response to request, use transfer system 190 and/or server 106 can transmit use and data file to client computer 102.For example, in one embodiment, server 106 can transmit as application flow using, with operation in the computing environment on client computer 102 15.

In certain embodiments, use the Citrix Access Suite that transfer system 190 comprises Citrix Systems company ^TMArbitrary part (for example MetaFrame or Citrix Presentation Server ^TM), and/or Microsoft's exploitation

In the Windows terminal service any one.In one embodiment, using transfer system 190 can be through remote display protocol or otherwise transmit one or more and be applied to client computer 102 or user through calculating based on remote computation or based on server.In yet another embodiment, application transfer system 190 can transmit one or more through application flow and be applied to client computer or user.

In one embodiment, use transfer system 190 and comprise policy engine 195, it is used to control and manage visit, the selection of application execution method and the transmission of application to using.In certain embodiments, policy engine 195 is confirmed one or more application that user or client computer 102 can be visited.In yet another embodiment, policy engine 195 confirms how application should be sent to user or client computer 102, for example manner of execution.In certain embodiments, use transfer system 190 a plurality of tranmission techniques are provided, therefrom the method for carrying out is used in selection, for example uses based on the calculating of server, local stream transmission or transmission and gives client computer 120 to be used for local the execution.

In one embodiment, the execution of client computer 102 request applications and the application transfer system 190 that comprises server 106 are selected the method for executive utilities.In certain embodiments, server 106 is from client computer 102 acceptance certificates.In yet another embodiment, server 106 is from the request enumerated of client computer 102 receptions for useful application.In one embodiment, respond the reception of this request or certificate, use transfer system 190 and enumerate a plurality of application programs that to use for client computer 102.Use transfer system 190 and receive the request of carrying out cited application.One of method of using transfer system 190 selection predetermined quantities is carried out cited application, the for example strategy of response policy engine.Use transfer system 190 and can select to carry out the method for application, make client computer 102 receive through carrying out the application output data that application program produced on the server 106.Use transfer system 190 and can select to carry out the method for application, make local machine 10 local executive utility after retrieval comprises a plurality of application files of application.In yet another embodiment, use the method that transfer system 190 can select to carry out application, to be applied to client computer 102 through network 104 stream transmissions.

Application can be carried out, operate or otherwise provided to client computer 102; Said application can be software, program or the executable instruction of any kind and/or form, for example the web browser of any kind and/or form, the client computer based on web, client-server application, thin-client computing client machine, ActiveX control or java applet, any other type that perhaps can on client computer 102, carry out and/or the executable instruction of form.In certain embodiments, application can be representative client 102 on server 106, carry out based on server or based on long-range application.In one embodiment; Server 106 can use any thin-client or remote display protocol show and output to client computer 102, said thin-independent computing architecture (ICA) agreement that client or remote display protocol are for example produced by the Citrix Systems company that is positioned at Florida State Ft.Lauderdale or the RDP (RDP) of producing by the Microsoft that is positioned at State of Washington Redmond.Application can be used the agreement of any kind, and it can be, for example, and HTTP client computer, FTP client computer, Oscar client computer or Telnet client computer.In other embodiments, use the software of any kind that comprising communicate by letter with VoIP is correlated with, for example soft IP phone.In a further embodiment, application comprises the arbitrary application that relates to real-time data communication, for example is used to transmit as a stream the application of video and/or audio.

In certain embodiments, server 106 or server zone 38 can move one or more application, and the application that thin-client calculates or long-range data representing is used for example is provided.In one embodiment, server 106 or server zone 38 are as a Citrix Access Suite that should be used for carrying out Citrix Systems company ^TMArbitrary part (for example MetaFrame or Citrix Presentation Server ^TM), and/or Microsoft's exploitation

In the Windows terminal service any one.In one embodiment, this application is the ICA client computer that is positioned at the exploitation of the Citrix Systems company of Florida State FortLauderdale.In other embodiments, this application comprises remote desktop (RDP) client computer by the Microsoft company exploitation that is positioned at State of Washington Redmond.In addition; Server 106 can move an application, and for example, it can provide the application server of E-mail service; For example by the Microsoft Exchange of the Microsoft manufactured that is positioned at State of Washington Redmond; Web or Internet server, perhaps desktop share service device, perhaps collaboration server.In certain embodiments, arbitrary application can comprise the service or the product that carries of posting of arbitrary type, for example is positioned at the GoToMeeting that the Citrix Online Division company of California Santa Barbara provides ^TM, be positioned at the WebEx that the WebEx company of California Santa Clara provides ^TM, perhaps be positioned at the Microsoft Office Live Meeting that the Microsoft company of State of Washington Redmond provides.

Still with reference to figure 1D, an embodiment of network environment can comprise monitoring server 106A.Monitoring server 106A can comprise the performance monitoring service 198 of any kind and form.Performance monitoring service 198 can comprise monitoring, measurement and/or management software and/or hardware, comprises data aggregation, set, analysis, management and report.In one embodiment, performance monitoring service 198 comprises one or more monitoring agents 197.Monitoring agent 197 comprises any software, hardware or its combination that is used on the device such as client computer 102, server 106 or equipment 200 and 205, carrying out monitoring, measurement and data collection activity.In certain embodiments, monitoring agent 197 comprises the script such as Visual Basic script or Javascript any kind and form.In one embodiment, monitoring agent 197 is carried out with respect to any application and/or the user transparent ground of device.In certain embodiments, monitoring agent 197 is not mounted boldly and operates with respect to application or client computer.In yet another embodiment, the installation of monitoring agent 197 and operation need not be used for any equipment of this application or device.

In certain embodiments, monitoring agent 197 is with preset frequency monitoring, measurement and collection data.In other embodiments, data are monitored, measure and collected to monitoring agent 197 based on the incident that detects any kind and form.For example, monitoring agent 197 can be collected data when detecting the request of the web page or receiving http response.In another example, monitoring agent 197 can be collected data when the arbitrary user's incoming event that detects such as click.Monitoring agent 197 can report or provide any data of monitoring, measuring or collect to monitor service 198.In one embodiment, monitoring agent 197 comes transmission information to give monitor service 198 according to arrangement of time or preset frequency.In yet another embodiment, monitoring agent 197 transmission information when detecting incident is given monitor service 198.

In certain embodiments, any Internet resources that connect of 197 pairs of monitor service 198 and/or monitoring agents such as client computer, server, server zone, equipment 200, equipment 205 or network or network infrastructure elements monitors and performance measurement.In one embodiment, monitor service 198 and/or monitoring agent 197 are carried out monitoring and the performance measurement such as any transport layer connection of TCP or UDP connection.In yet another embodiment, monitor service 198 and/or 197 monitoring and Measurement Network stand-by period of monitoring agent.In yet another embodiment, monitor service 198 and/or monitoring agent 197 monitoring and measurement bandwidth usage.

In other embodiments, monitor service 198 and/or monitoring agent 197 monitoring and measuring terminals subscriber response times.In certain embodiments, monitor service 198 is carried out monitoring and the performance measurement of using.In yet another embodiment, monitor service 198 and/or monitoring agent 197 implement the monitoring and the performance measurement of any session or the connection of application.In one embodiment, the performance of monitor service 198 and/or monitoring agent 197 monitoring and measurement browser.In yet another embodiment, monitor service 198 and/or monitoring agent 197 monitoring and measurement are based on the performance of the affairs of HTTP.In certain embodiments, monitor service 198 and/or monitoring agent 197 monitoring and measurement IP phone (VoIP) are used or performance of sessions.In other embodiments, the performance of the remote display protocol application of monitor service 198 and/or monitoring agent 197 monitoring and measurement such as ICA client computer or RDP client computer.In yet another embodiment, the performance of the Streaming Media of monitor service 198 and/or monitoring agent 197 monitoring and measurement any kind and form.In a further embodiment, monitor service 198 and/or monitoring agent 197 monitoring and measurement are posted the application or the software that carry and are promptly served (Software-As-A-Service, SaaS) performance of transport model.

In certain embodiments, monitor service 198 and/or monitoring agent 197 are carried out and monitoring and the performance measurement of using relevant one or more affairs, request or response.In other embodiments, any part of monitor service 198 and/or monitoring agent 197 monitoring and measurement application layer storehouse, for example any .NET or J2EE call.In one embodiment, monitor service 198 and/or monitoring agent 197 monitoring and measured database or SQL affairs.In yet another embodiment, monitor service 198 and/or monitoring agent 197 are monitored and are measured any method, function or API (API) and call.

In one embodiment, 197 pairs of monitor service 198 and/or monitoring agents are monitored and performance measurement from the application of server to client machine and/or the transmission of data via the one or more equipment such as equipment 200 and/or equipment 205.In certain embodiments, the performance of the transmission of monitor service 198 and/or monitoring agent 197 monitoring and measurement virtualization applications.In other embodiments, the performance of the transmission of monitor service 198 and/or monitoring agent 197 monitoring and the application of measurement streaming.In yet another embodiment, monitor service 198 and/or monitoring agent 197 monitoring and measurement transmit desktop application is carried out desktop application to client computer and/or on client computer performance.In yet another embodiment, the performance of monitor service 198 and/or monitoring agent 197 monitoring and measuring customer machine/server application.

In one embodiment, monitor service 198 and/or monitoring agent 197 are designed and are configured to application transfer system 190 the application performance management is provided.For example, monitor service 198 and/or monitoring agent 197 can be monitored, measure and manage via Citrix and represent that server (Citrix Presentation Server) transmits the performance of using.In this example, monitor service 198 and/or the independent ICA session of monitoring agent 197 monitoring.Monitor service 198 and/or monitoring agent 197 can be measured total and each conversational system resource and use, and use and the networking performance.Monitor service 198 and/or monitoring agent 197 can identify effective server (active server) for given user and/or user conversation.In certain embodiments, monitor service 198 and/or monitoring agent 197 monitoring connect in the rear end of using between transfer system 190 and application and/or the database server.Monitor service 198 and/or monitoring agent 197 can be measured network stand-by period, delay and the capacity of each user conversation or ICA session.

In certain embodiments, monitor service 198 and/or monitoring agent 197 measurements and monitoring are used for the storer such as total storer use, each user conversation and/or each process of using transfer system 190.In other embodiments, monitor service 198 and/or monitoring agent 197 measurements and monitoring are used such as the CPU of the application transfer system 190 of total CPU use, each user conversation and/or each process.In yet another embodiment, monitor service 198 and/or monitoring agent 197 measurements and monitoring sign in to application, server or the application required time of transfer system of representing server such as Citrix.In one embodiment, the duration that monitor service 198 and/or monitoring agent 197 are measured and supervisory user is logined application, server or application transfer system 190.In certain embodiments, the effective and invalid session count of application, server or the session of application transfer system is measured and monitored to monitor service 198 and/or monitoring agent 197.In yet another embodiment, monitor service 198 and/or monitoring agent 197 are measured and the supervisory user session stand-by period.

In yet another embodiment, the server index of any kind and form is measured and monitored to monitor service 198 and/or monitoring agent 197.In one embodiment, monitor service 198 and/or monitoring agent 197 measurements are used the index relevant with magnetic disk memory with monitoring with Installed System Memory, CPU.In yet another embodiment, monitor service 198 and/or the monitoring agent 197 measurements index relevant with page fault with monitoring are such as the per second page fault.In other embodiments, the index of two-way time is measured and monitored to monitor service 198 and/or monitoring agent 197.In yet another embodiment, monitor service 198 and/or monitoring agent 197 measurements and monitoring and application crashes, mistake and/or the relevant index of termination.

In certain embodiments, monitor service 198 comprises any product embodiments that is called as EdgeSight of being produced by the Citrix Systems company that is positioned at Florida State Ft.Lauderdale with monitoring agent 198.In yet another embodiment, performance monitoring service 198 and/or monitoring agent 198 comprise arbitrary part of the product embodiments that is called as the TrueView product suite of being produced by the Symphoniq company that is positioned at California Palo Alto.In one embodiment, performance monitoring service 198 and/or monitoring agent 198 comprise any part of the product embodiments that is called as the TeaLeafCX product suite of being produced by the TeaLeaf technology company that is positioned at California San Francisco.In other embodiments, performance monitoring service 198 and/or monitoring agent 198 comprise by the BMC Software that is positioned at Texas Houston produce such as any part of BMC performance manager with the commercial occupation management product of patrol product (BMC Performance Manager and Patrol products).

Client computer 102, server 106 and equipment 200 can be deployed as and/or carry out on the calculation element of any kind and form, such as can and carrying out computing machine, network equipment or the equipment of operation described herein at the network communication of any kind and form.Fig. 1 E and 1F have described the block diagram of the calculation element 100 of the embodiment that can be used for implementing client computer 102, server 106 or equipment 200.Shown in Fig. 1 E and 1F, each calculation element 100 comprises CPU 101 and main storage unit 122.Shown in Fig. 1 E, calculation element 100 can comprise visible display device 124, keyboard 126 and/or such as the indicating device 127 of mouse.Each calculation element 100 also can comprise other selectable unit, for example one or more input/output device 130a-130b (total use Reference numeral 130 expressions), and the cache memory 140 of communicating by letter with CPU 101.

CPU 101 is responses and handles from any logical circuit of the instruction of main storage unit 122 taking-ups.In many examples, CPU is provided by microprocessor unit, for example: the microprocessor unit of being made by the Intel Company of California Mountain View; The microprocessor unit of making by the motorola inc of Illinois Schaumburg; The microprocessor unit of making by the Transmeta Company of California Santa Clara; RS/6000 processor by the International Business Machines manufactured of New York White Plains; Perhaps by the microprocessor unit of the Advanced Micro Devices manufactured of California Sunnyvale.Calculation element 100 can be based in these processors any, perhaps can be according to any other processor of that kind operation described herein.

Main storage unit 122 can be can store data and allow microprocessor 101 directly to visit one or more memory chips of any memory location, for example static RAM (SRAM), burst SRAM or synchronization burst SRAM (BSRAM), dynamic RAM DRAM, fast page mode DRAM (FPM DRAM), enhancement mode DRAM (EDRAM), growth data output RAM (EDO RAM), growth data output DRAM (EDO DRAM), burst type growth data output DRAM (BEDO DRAM), enhancement mode DRAM (EDRAM), synchronous dram (SDRAM), JEDEC SRAM, PC100 SDRAM, double data rate SDRAM (DDR SDRAM), enhancement mode SRAM (ESDRAM), synchronization link DRAM (SLDRAM), direct Rambus DRAM (DRDRAM) or ferroelectric RAM (FRAM).Primary memory 122 can be based on above-mentioned storage chip any, any other storage availability chip that perhaps can as described herein, move.In the embodiment shown in Fig. 1 E, processor 101 communicates through system bus 150 (being described in more detail below) and primary memory 122.Fig. 1 E has described the embodiment of the calculation elements 100 that processor therein directly communicates by letter with primary memory 122 through port memory 103.For example, in Fig. 1 F, primary memory 122 can be DRDRAM.

Fig. 1 F has described that primary processor 101 is through the embodiment of second bus and cache memory 140 direct communications therein, and second bus is also referred to as the dorsal part bus sometimes.Among other embodiment, primary processor 101 using system buses 150 are communicated by letter with cache memory 140.Cache memory 140 has than primary memory 122 response time faster usually, and is provided by SRAM, BSRAM or EDRAM usually.In the embodiment shown in Fig. 1 F, processor 101 communicates through local system bus 150 and a plurality of I/O devices 130.Can use various bus that CPU 101 is connected to any I/O device 130, said bus comprises VESA VL bus, isa bus, eisa bus, MCA (MCA) bus, pci bus, PCI-X bus, PCI-Express bus or NuBus.For the I/O device is the embodiment of video display 124, and processor 101 can use advanced graphics port (AGP) to communicate by letter with display 124.Fig. 1 F has explained the embodiment of primary processor 101 through ultra transmission (HyperTransport), quick I/O or the direct computing machine 100 of communicating by letter with I/O device 130 of InfiniBand.Fig. 1 F has also described the embodiment that mixes local bus and direct communication therein: processor 101 uses local interconnect bus and I/O device 130 to communicate, and direct simultaneously and I/O device 130 communicates.

Calculation element 100 can be supported any suitable erecting device 116, for example is used to receive tape drive, USB device, the hard disk drive of floppy disk, CD-ROM drive, CD-R/RW driver, the DVD-ROM driver of the floppy disk as 3.5 inches, 5.25 inches disks or ZIP disk, multiple form or is suitable for installing as the software of any client proxy 120 or its part and any other device of program.Calculation element 100 can also comprise memory storage 128; Such as one or more hard disk drive or RAID; Be used for storage operating system and other related software, and be used to store Application Software Program such as any program that relates to client proxy 120.Perhaps, can use any of erecting device 116 as memory storage 128.In addition; But operating system and software can be from for example guiding the boot media operation of CD; Such as

a kind of guided CD that is used for GNU/Linux, this can guide, and CD can distribution obtains as GNU/Linux from knoppix.net.

In addition; Calculation element 100 can comprise through the network interface 118 of multiple connecting interface to Local Area Network, wide area network (WAN) or the Internet; Said multiple connection includes but not limited to standard telephone line, LAN or wide-area network link (for example 802.11; T1, T3,56kb, X.25), some combinations of broadband connection (like ISDN, frame relay, ATM), wireless connections or above-mentioned any or all connection.Network interface 118 can comprise built-in network adapter, NIC, PCMCIA network card, card bus network adapter, wireless network adapter, USB network adapter, modulator-demodular unit or be applicable to any miscellaneous equipment of calculation element 100 interfaces to the network of any kind that can communicate by letter and carry out operation described herein.Can comprise various I/O device 130a-130n in the calculation element 100.Input media comprises keyboard, mouse, Trackpad, trace ball, microphone and plotting sheet.Output unit comprises video display, loudspeaker, ink-jet printer, laser printer and thermal printer.Shown in Fig. 1 E, I/O device 130 can be by 123 controls of I/O controller.The I/O controller can be controlled one or more I/O devices, for example keyboard 126 and indicating device 127 (like mouse or light pen).In addition, the I/O device can also provide memory storage 128 and/or medium 116 is installed for calculation element 100.In other embodiments, calculation element 100 can provide USB to connect to receive hand-held USB memory storage, the USB flash memory drive wire of the equipment of for example being produced by the Twintech Industry company that is positioned at California Los Alamitos.

In certain embodiments, calculation element 100 can comprise a plurality of display device 124a-124n or coupled, and these display device can be identical or different type and/or form separately.Thereby; Any I/O device 130a-130n and/or I/O controller 123 can comprise the combination of suitable hardware, software or the hardware and software of arbitrary type and/or form, connect and use a plurality of display device 124a-124n to support, to allow or to provide through calculation element 100.For example, calculation element 100 can comprise video adapter, video card, driver and/or the storehouse of any kind and/or form, with display device 124a-124n interface, communication, be connected or otherwise use display device.In one embodiment, video adapter can comprise a plurality of connectors with a plurality of display device 124a-124n interfaces.In other embodiments, calculation element 100 can comprise a plurality of video adapters, the one or more connection among each video adapter and the display device 124a-124n.In certain embodiments, arbitrary part of the operating system of calculation element 100 can be arranged to and use a plurality of display 124a-124n.In other embodiments, one or more can being provided by one or more other calculation elements among the display device 124a-124n is such as the calculation element 100a and the 100b that for example are connected with calculation element 100 through network.These embodiment can comprise and are designed and are configured to the display device of another computing machine software as arbitrary type of the second display device 124a of calculation element 100.Those of ordinary skill in the art can be familiar with and understand the whole bag of tricks and the embodiment that can calculation element 100 be configured to have a plurality of display device 124a-124n.

In a further embodiment; I/O device 130 can be the bridge 170 between system bus 150 and the external communication bus, and for example usb bus, Apple desktop bus, RS-232 are connected in series for said external communication bus, SCSI bus, FireWire bus, FireWire800 bus, industry ethernet, AppleTalk bus, GBIC bus, asynchronous transfer mode bus, HIPPI bus, super HIPPI bus, SerialPlus bus, SCI/LAMP bus, fiber channel bus or serial SCSI bus.

That type calculation element of describing among Fig. 1 E and the 1F 100 is operated down in the scheduling of control task with to the control of the operating system of the visit of system resource usually.Calculation element 100 can move any operating system; Like

Windows operating system; The Unix and the (SuSE) Linux OS of different release versions; Any embedded OS of MAC

that is used for any version of macintosh computer; Any real time operating system; Any operating system of increasing income; Any proprietary operating systems, any operating system that is used for mobile computing device, perhaps any other can move and accomplish the operating system of operation described here on calculation element.Typical operating system comprises: WINDOWS 3.x, WINDOWS 95, WINDOWS 98, WINDOWS 2000, WINDOWS NT 3.51, WINDOWS NT 4.0, WINDOWS CE and WINDOWS XP, and all these are produced by the Microsoft that is positioned at State of Washington Redmond; MacOS by the Apple computer product that is positioned at California Cupertino; OS/2 by the International Business Machine Corporation's product that is positioned at New York Armonk; And by the (SuSE) Linux OS that can freely use of the Caldera company issue that is positioned at Utah State Salt Lake City or the Unix operating system of any kind and/or form, and other.

In other embodiments, calculation element 100 can have different processors, operating system and the input equipment that meets this device.For example, in one embodiment, computing machine 100 is Treo180,270,1060,600 or 650 smart phones of being produced by Palm company.In this embodiment, the Treo smart phone is operated under the control of PalmOS operating system, and comprises stylus input media and five navigation device.In addition, calculation element 100 can be any workstation, desktop computer, on knee or notebook, server, handheld computer, mobile phone, any other computing machine, maybe can communicate by letter and have enough processor abilities and memory capacity calculating or the telecommunication installation with other form of carrying out operation described herein.

Shown in Fig. 1 G, calculation element 100 can comprise a plurality of processors, can be provided for a not only data pieces is carried out a plurality of instructions simultaneously or carried out the function of an instruction simultaneously.In certain embodiments, calculation element 100 can comprise the parallel processor with one or more nuclears.In of these embodiment, calculation element 100 is shared drive LPT devices, has a plurality of processors and/or a plurality of processor core, and all free memories are conducted interviews as a global address space.In another of these embodiment, calculation element 100 is distributed memory LPT devices, has a plurality of processors, each processor access local storage.In another of these embodiment, calculation element 100 existing shared storeies only have the storer by par-ticular processor or processor subset access again.In another of these embodiment, like the calculation element 100 of multi-core microprocessor two or more independent processors are combined in the encapsulation, usually in an integrated circuit (IC).In another of these embodiment; Calculation element 100 comprises the chip of (the CELL BROADBAND ENGINE) framework that has the unit wideband engine; And comprise high power treatment device unit and a plurality of synergetic unit; High power treatment device unit and a plurality of synergetic unit link together through the inner high speed bus, can the inner high speed bus be called the cell interconnection bus.

In certain embodiments, processor is provided for a plurality of data slice are carried out simultaneously the function of single instruction (SIMD).Among other embodiment, processor is provided for a plurality of data slice are carried out simultaneously the function of a plurality of instructions (MIMD).Among another embodiment, processor can use the combination in any of SIMD and MIMD nuclear in single assembly.

In certain embodiments, calculation element 100 can comprise graphics processing unit.Shown in Fig. 1 H in of these embodiment, calculation element 100 comprises at least one CPU 101 and at least one graphics processing unit.In another of these embodiment, calculation element 100 comprises at least one parallel processing element and at least one graphics processing unit.In another of these embodiment, calculation element 100 comprises a plurality of processing units of any type, and one in a plurality of processing units comprises graphics processing unit.

Among some embodiment, on behalf of the user of client's calculation element 100b, the first calculation element 100a carry out application.Among another embodiment, calculation element 100 is carried out virtual machine, and it provides the execution session, in this session, represents the user of client's calculation element 100b to carry out application.In of these embodiment, carrying out session is to post the desktop session of carrying.In another of these embodiment, calculation element 100 is carried out terminal server sessions.Terminal server session can provide posts the desktop environment of carrying.In another of these embodiment, to carry out session the visit to computing environment is provided, computing environment can comprise following one or more: application, a plurality of application, desktop application and the desktop session that can carry out one or more application.

B. The equipment framework

Fig. 2 A illustrates an example embodiment of equipment 200.Provide equipment 200 frameworks of Fig. 2 A only to be used for example, be not intended to as restrictive framework.As shown in Figure 2, equipment 200 comprises hardware layer 206 and the software layer that is divided into user's space 202 and kernel spacing 204.

Hardware layer 206 provides hardware element, and the program in kernel spacing 204 and user's space 202 is performed on this hardware element with service.Hardware layer 206 also provides structure and element, and with regard to equipment 200, these structures and element allow the program in kernel spacing 204 and user's space 202 not only to carry out data communication in inside but also carry out data communication with the outside with serving.As shown in Figure 2; Hardware layer 206 comprises the processing unit 262 that is used for software program for execution and service; Be used for storing software and memory of data 264; Be used for through the Network Transmission and the network port 266 that receives data, and be used to carry out the encryption processor 260 of the function treatment relevant through the data of Network Transmission and reception with secure sockets layer.In certain embodiments, CPU 262 function of device 260 that can in independent processor, perform encryption processing.In addition, hardware layer 206 can comprise the multiprocessor that is used for each processing unit 262 and encryption processor 260.Processor 262 can comprise above combination Fig. 1 E and the described arbitrary processor 101 of 1F.For example, in one embodiment, equipment 200 comprises the first processor 262 and second processor 262 '.In other embodiments, processor 262 or 262 ' comprises polycaryon processor.

Though the hardware layer 206 of the equipment 200 that illustrates has encryption processor 260 usually, processor 260 can be the processor of carrying out the function that relates to any cryptographic protocol, for example secure sockets layer (SSL) or Transport Layer Security (TLS) agreement.In certain embodiments, processor 260 can be general processor (GPP), and in a further embodiment, can be the executable instruction that is used to carry out any safe related protocol processing.

Though the hardware layer 206 of equipment 200 has comprised some element among Fig. 2; But the hardware components of equipment 200 or assembly can comprise any kind of calculation element and element, hardware or the software of form, the calculation element 100 that for example combines Fig. 1 E and 1F to illustrate and discuss here.In certain embodiments, equipment 200 can comprise the calculating or the network equipment of server, gateway, router, switch, bridge or other type, and has relevant therewith any hardware and/or software element.

The operating system of equipment 200 is distributed, is managed or separates the available system storer in addition to kernel spacing 204 and user's space 204.In the software architecture 200 of example, operating system can be the Unix operating system of any kind and/or form, although not restriction like this of the present invention.Like this; Equipment 200 can move any operating system, like the Unix and the (SuSE) Linux OS of

Windows operating system of any version, different editions, be used for any embedded OS of Mac

of any version of macintosh computer, any network operating system, any real time operating system, any open-source operating system, any special purpose operating system, be used for mobile computing device or network equipment any operating system, or can operate on the equipment 200 and carry out any other operating system of operation described herein.

Keep kernel spacing 204 and be used to move kernel 230, kernel 230 comprises any device driver, kernel extensions or other kernel related softwares.Just as what those skilled in the art knew, kernel 230 is cores of operating system, and visit, control and management to the related hardware element of resource and equipment 104 are provided.According to the embodiment of equipment 200, kernel spacing 204 comprises also and a plurality of network services or the process of cache manger 232 collaborative works that cache manger 232 is also referred to as integrated high-speed cache sometimes, and its benefit will describe in further detail here.In addition, the embodiment of kernel 230 will depend on the embodiment through the operating system of equipment 200 installations, configuration or other uses.

In one embodiment, equipment 200 comprises a network stack 267, for example based on the storehouse of TCP/IP, is used for communicating by letter with client computer 102 and/or server 106.In one embodiment, use network stack 267 to communicate by letter with first network (for example network 108) and second network 110.In certain embodiments; Equipment 200 terminations first transport layer connects, and for example the TCP of client computer 102 connects, and sets up second transport layer connection to server 106 that client computer 102 is used; For example, second transport layer that terminates in equipment 200 and server 106 is connected.Can set up first and second transport layers through independent network stack 267 connects.In other embodiments, equipment 200 can comprise a plurality of network stacks, for example 267 or 267 ', and can set up or stop first transport layer at a network stack 267 and connect, on second network stack 267 ', can set up or stop the connection of second transport layer.For example, a network stack is used in and receives on first network and the transmission network grouping, and another network stack is used on second network, receiving and transmission network divides into groups.In one embodiment, network stack 267 comprises and is used to the impact damper 243 that one or more network packet are ranked that wherein network packet is by equipment 200 transmission.

As shown in Figure 2, kernel spacing 204 comprises the integrated Packet engine of cache manger 232, high-velocity bed 2-7 240, crypto engine 234, policy engine 236 and multi-protocols compressed logic 238.In kernel spacing 204 or kernel mode rather than user's space 202 operation these assemblies or process 232,240,234,236 and 238 improve in these assemblies each independent with the performance that combines.Kernel operations means that these assemblies or process 232,240,234,236 and 238 move in the nuclear address space of the operating system of equipment 200.For example; In kernel mode operation crypto engine 234 through mobile encrypted and decryption oprerations in endorse the improvement encryption performance, thereby can reduce storage space or the quantity of kernel thread and storage space in user model or the transmission between the thread in kernel mode.For example, the data that obtain at kernel mode maybe not need be transmitted or are copied process or the thread that operates in user model to, for example from kernel-level data to the user-level data structure.In yet another aspect, also can reduce the quantity that the context between kernel mode and the user model switches.In addition, any assembly or process 232,240,235,236 with 238 synchronously with communicate by letter and in kernel spacing 204, can be performed more efficient.

In certain embodiments, assembly 232,240,234,236 and 238 any part can be moved in kernel spacing 204 or operate, and other part of these assemblies 232,240,234,236 and 238 can be moved in user's space 202 or operate.In one embodiment, equipment 200 uses kernel-level data that the visit to any part of one or more network packet is provided, and for example, comprises from the request of client computer 102 or from the network packet of the response of server 106.In certain embodiments, can pass through to the transport layer driver interface or the filtrator acquisition kernel-level data of network stack 267 by Packet engine 240.Kernel-level data can comprise Network or the grouping that receives or send through kernel spacing 204 addressable any interfaces relevant with network stack 267 and/or data, by network stack 267.In other embodiments, any assembly or process 232,240,234,236 and 238 can use kernel-level data to come the operation of the needs of executive module or process.In an example; When using kernel-level data, assembly 232,240,234,236 and 238 moves in kernel mode 204, and In yet another embodiment; When using kernel-level data, assembly 232,240,234,236 and 238 moves in user model.In certain embodiments, kernel-level data can be copied or be delivered to second kernel-level data, or any desired user-level data structure.

Cache manger 232 can comprise any combination of software, hardware or software and hardware; So that cache access, control and the management to the content of any kind and form to be provided, object or the object of the dynamic generation of service is provided by source server 106 for example.Handle and data, object or the content of storage can comprise the data of any form (for example SGML) by cache manger 232, perhaps the data of any kind of the communication through any agreement.In certain embodiments; Cache manger 232 duplicates and is stored in other local raw data or the previous data of calculating, producing or transmit; Wherein, need the longer access time to obtain, to calculate or otherwise to obtain raw data with respect to reading the cache memory element.In case data are stored in the cache stores element, therefore the copy through access cache rather than regain or recomputate raw data and can carry out subsequent operation has reduced the access time.In certain embodiments, cache element can comprise the data object in the storer 264 of equipment 200.In other embodiments, the cache stores element can include than storer 264 storer of access time faster.In yet another embodiment, cache element can comprise the arbitrary type of equipment 200 and the memory element of form, such as the part of hard disk.In certain embodiments, processing unit 262 can provide the cache memory that is used by cache manger 232.In yet another embodiment, cache manger 232 can use any part of storer, memory block or processing unit and combination to come cached data, object or other content.

In addition, cache manger 232 comprises any logic, function, rule or the operation of arbitrary embodiment of the technology that is used to carry out equipment 200 described herein.For example, cache manger 232 comprises the termination based on cycle ineffective time, perhaps receives the logical OR function that invalid command makes object invalidation from client computer 102 or server 106.In certain embodiments, cache manger 232 can be used as program, service, process or the task of in kernel spacing 204, carrying out and operates, and in other embodiments, in user's space 202, carries out.In one embodiment, the first of cache manger 232 carries out in user's space 202, and second portion is carried out in kernel spacing 204.In certain embodiments; Cache manger 232 can comprise the general processor (GPP) of any kind, or the integrated circuit of any other type, for example field programmable gate array (FPGA); Programmable logic device (PLD), perhaps special IC (ASIC).

Policy engine 236 can comprise for example intelligent statistics engine or other programmable applications.In one embodiment, policy engine 236 provides configuration mechanism to allow User Recognition, appointment, definition or configuring high speed caching strategy.Policy engine 236, in certain embodiments, also reference-to storage is to support data structure, for example backup sheet or hash table determines with the cache policies of launching user's selection.In other embodiments; Except visit, control and management to any function of being carried out by equipment 200 of safety, Network, access to netwoks, compression or other or operation, policy engine 236 can comprise that any logic, rule, function or operation are to confirm and visit, control and the management to object, data or the content of 200 high-speed caches of equipment be provided.Other embodiment of specific cache policy further describes here.

In certain embodiments, policy engine 236 can provide configuration mechanism with allow User Recognition, appointment, definition or configuration guide to include but not limited to describe among Fig. 2 B such as vServers 275, VPN function 280, Intranet IP function 282, function of exchange 284, DNS function 286, quicken the strategy of behavior of any other parts or function of equipment of the parts of function 288, application firewall function 290 and monitoring agent 197.In other embodiments, policy engine 236 can be checked, estimate, realize or otherwise generation effect, and can instruct the operation of one or more functions of the equipments in response to strategy in response to arbitrary configured strategy.

Crypto engine 234 comprises any logic, business rules, function or the operation that is used to control such as the processing of any safe related protocol of SSL or TLS or any function of wherein relating to.For example, the network packet that crypto engine 234 is encrypted and deciphering is transmitted through equipment 200, or its any part.But crypto engine 234 also representative client 102a-102n, server 106a-106n or equipment 200 is provided with or sets up SSL or TLS connection.Therefore, crypto engine 234 provides unloading and the acceleration that SSL handles.In one embodiment, crypto engine 234 uses tunnel protocol to be provided at the VPN between client computer 102a-102n and server 106a-106n.In certain embodiments, crypto engine 234 is communicated by letter with encryption processor 260.In other embodiments, crypto engine 234 comprises the executable instruction that operates on the encryption processor 260.

Multi-protocols compression engine 238 comprises any logic, business rules, function or the operation that is used to compress one or more network packet agreements (any agreement of for example being used by the network stack 267 of equipment 200).In one embodiment; Multi-protocols compression engine 238 bi-directional compression are arbitrary agreement based on TCP/IP between client computer 102a-102n and server 106a-106n, comprises that messages application DLL (MAPI) (Email), FTP (FTP), HTTP(Hypertext Transport Protocol), CIFS (CIFS) agreement (file transfer), independent computing architecture (ICA) agreement, RDP (RDP), wireless application protocol (wap), mobile IP protocol and IP go up voice (VoIP) agreement.In other embodiments, multi-protocols compression engine 238 provides the compression based on the agreement of HTML(Hypertext Markup Language), and in certain embodiments, the compression of any SGML is provided, for example extend markup language (XML).In one embodiment, multi-protocols compression engine 238 provides the compression of any high-performance agreement, for example is designed for any agreement of equipment 200 to equipment 200 communications.In yet another embodiment; Multi-protocols compression engine 238 uses the transmission control protocol of revising to compress any load or any communication of any communication, for example the congested forecast agreement and the TCP fraud protocol (TCP spoofing protocol) of affairs TCP (T/TCP), the TCP (TCP-SACK) that has the selection affirmation, the TCP (TCP-LW) that has big window, for example TCP-Vegas agreement.

Same; Multi-protocols compression engine 238 is quickened the performance via desktop client and even mobile client access application for the user; Said desktop client is Micosoft Outlook and non-web thin client for example; Such as by any client computer that general enterprise application started as Oracle, SAP and Siebel, said mobile client is palm PC for example.In certain embodiments, through carrying out and integrated in that kernel mode 204 is inner with the packet processing engine 240 of accesses network storehouse 267, any agreement that multi-protocols compression engine 238 can compression-tcp/IP agreement be carried, for example any application layer protocol.

The integrated Packet engine 240 of high-velocity bed 2-7 is also referred to as packet processing engine usually, or Packet engine, is responsible for the management that equipment 200 receives through the network port 266 and the kernel level of the grouping of transmission is handled.The integrated Packet engine 240 of high-velocity bed 2-7 can comprise the impact damper that is used for the one or more network packet of queuing during the processing that for example receives the grouping of network packet and transmission network.In addition, the integrated Packet engine 240 of high-velocity bed 2-7 is communicated by letter with one or more network stacks 267 to send and to receive network packet through the network port 266.The integrated Packet engine 240 of high-velocity bed 2-7 and crypto engine 234, cache manger 232, policy engine 236 and 238 collaborative works of multi-protocols compressed logic.More specifically; Configuration crypto engine 234 is handled to carry out the SSL that divides into groups; Collocation strategy engine 236 relates to the function of service management with execution; For example the request level content is switched and the request level high-speed cache is redirected, and configuration multi-protocols compressed logic 238 relates to the function of data compression and decompression with execution.

The integrated Packet engine 240 of high-velocity bed 2-7 comprises packet transaction timer 2 42.In one embodiment, packet transaction timer 2 42 provides one or more time intervals to handle to trigger input, for example, receives or output (i.e. transmission) network packet.In certain embodiments, the integrated Packet engine 240 of high-velocity bed 2-7 is handled network packet in response to timer 2 42.Packet transaction timer 2 42 provides the signal of any kind and form with relevant incident of notice, triggering or transmission time, interval or generation to Packet engine 240.In many examples, packet transaction timer 2 42 is with Millisecond operation, for example 100ms, 50ms or 25ms.For example; In some instances; Packet transaction timer 2 42 provides the time interval or otherwise makes handles network packet by the integrated Packet engine 240 of high-velocity bed 2-7 with the 10ms time interval, and in other embodiments, makes the integrated Packet engine 240 of high-velocity bed 2-7 handle network packet with the 5ms time interval; And in a further embodiment, be short to 3,2 or the 1ms time interval.The integrated Packet engine 240 of high-velocity bed 2-7 can be connected with crypto engine 234, cache manger 232, policy engine 236 and multi-protocols compression engine 238 during operation, integrated or communication.Therefore, in response to packet transaction timer 2 42 and/or Packet engine 240, can carry out any logic, function or the operation of crypto engine 234, cache manger 232, policy engine 236 and multi-protocols compression engine 238.Therefore; The time interval granularity that is providing by packet transaction timer 2 42; Can carry out any logic, function or the operation of crypto engine 234, cache manger 232, policy engine 236 and multi-protocols compression engine 238, for example, the time interval is less than or equals 10ms.For example, in one embodiment, cache manger 232 can be carried out the termination of the object of any high-speed cache in response to the integrated Packet engine 240 of high-velocity bed 2-7 and/or packet transaction timer 2 42.In yet another embodiment, are set to the termination of the object of high-speed cache or ineffective time the particle size fraction identical, for example every 10ms with the time interval of packet transaction timer 2 42.

Different with kernel spacing 204, user's space 202 is by user mode application or in the storage area or the part of the employed operating system of program of user model operation.User mode application is access kernel space 204 and use service call with the visit kernel services directly.As shown in Figure 2, the user's space 202 of equipment 200 comprises graphical user interface (GUI) 210, command line interface (CLI) 212, shell service (shell service) 214, health monitoring program 216 and guards (daemon) service 218.GUI 210 and CLI 212 provide system manager or other users can be mutual with it and the device of opertaing device 200 operations, for example the operating system through equipment 200.GUI 210 and CLI 212 can comprise the code that operates in user's space 202 or the interior core framework 204.GUI 210 can be the graphical user interface of any kind or form, can appear through program or the application (like browser) by any kind of text, figure or other forms.CLI 212 can be the order line or the text based interface of any kind and form, the order line that for example provides through operating system.For example, CLI 212 can comprise shell, and this shell is to use family and the interactional instrument of operating system.In certain embodiments, can CLI 212 be provided through the shell of bash, csh, tcsh or ksh type.Shell service 214 comprises that program, service, task, process or executable instruction are to support mutual with equipment 200 or operating system through GUI 210 and/or CLI 212 by the user

Health monitoring program 216 is used for monitoring, check, report and guaranteeing that network system normally moves, and the user is just receiving the content of request through network.Health monitoring program 216 comprises one or more programs, service, task, process or executable instruction, for any behavior of watch-dog 200 provides logic, rule, function or operation.In certain embodiments, 216 interceptions of health monitoring program and inspection are through any Network of equipment 200 transmission.In other embodiments; Health monitoring program 216 is connected with one or more following equipment through any suitable method and/or mechanism: crypto engine 234; Cache manger 232, policy engine 236, multi-protocols compressed logic 238; Packet engine 240, the service of guarding 218 and shell service 214.Therefore, health monitoring program 216 can be called state, situation or the health of any API (API) with any part of definite equipment 200.For example, health monitoring program 216 can periodically be checked the inquiry of (ping) or transmit status and moved so that whether scrutiny program, process, service or task be movable and current.In yet another embodiment, health monitoring program 216 can check that any state, mistake or the history log that are provided by any program, process, service or task are to confirm any situation, state or the mistake of equipment 200 any parts.

The service of guarding 218 is programs of moving or in background, move continuously, and the periodic service request of treatment facility 200 receptions.In certain embodiments, the service of guarding can be transmitted request to other programs or process (for example suitable another service of guarding 218).As known in those skilled in the art, the operation that the service of guarding 218 can unmanned monitoring, carrying out continuous or periodic system scope function, the task of any needs is perhaps carried out in for example network control.In certain embodiments, one or more services of guarding 218 operate in the user's space 202, and in other embodiments, one or more services of guarding 218 operate in kernel spacing.

Refer now to Fig. 2 B, described another embodiment of equipment 200.Generally speaking, equipment 200 provides one or more in following service, function or the operation: the SSL VPN that is used for the communication between one or more client computer 102 and the one or more server 106 is communicated with 280, exchange/load balance 284, domain name service resolve 286, acceleration 288 and application firewall 290.Each of server 106 can provide one or more Internet-related services 270a-270n (being called service 270).For example, server 106 can provide http service 270.Equipment 200 comprises one or more virtual server or virtual Internet protocol server, is called vServer 275, vS 275, VIP server or only is VIP 275a-275n (being also referred to as vServer 275 here).VServer 275 is according to the configuration of equipment 200 and operation receives, tackles or the otherwise communication between processing client 102 and the server 106.

VServer 275 can comprise any combination of software, hardware or software and hardware.VServer275 can be included in any kind that moves in user model 202 in the equipment 200, kernel mode 204 or its any combination and program, service, task, process or the executable instruction of form.VServer275 comprises any logic, function, rule or operation, to carry out any embodiment of technology described herein, such as SSL VPN 280, conversion/load balance 284, domain name service parsing 286, acceleration 288 and application firewall 290.In certain embodiments, vServer 275 is established to the connection of the service 270 of server 106.Service 275 can comprise any program, application, process, task or the executable instruction set of the equipment that can be connected to 200, client computer 102 or vServer 275 and communication with it.For example, service 275 can comprise web server, http-server, ftp, Email or database server.In certain embodiments, service 270 is finger daemon or network drive, is used to monitor, receive and/or send the communication of application, such as Email, database or enterprise application.In certain embodiments, service 270 can be communicated by letter on specific I P address or IP address and port.

In certain embodiments, one or more strategy of vServer 275 application strategy engines 236 is to the network service between client computer 102 and the server 106.In one embodiment, this strategy is relevant with vServer 275.In yet another embodiment, this strategy is based on user or user's group.In yet another embodiment, strategy is organized with Any user of communicating by letter through equipment 200 or user for general and be applied to one or more vServer 275a-275n.In certain embodiments; The strategy of policy engine have should strategy based on any content application of communication condition; Stem in content such as the Internet protocol address of communication, port, protocol type, the grouping or field, the context of perhaps communicating by letter are such as the sign or the attribute of user, user's group, vServer 275, transport layer connection and/or client computer 102 or server 106.

In other embodiments, equipment 200 is communicated by letter or interface with policy engine 236, so that confirm the checking and/or the mandate of long-distance user or remote client 102, with computing environment 15, application and/or the data file of visit from server 106.In yet another embodiment, equipment 200 is communicated by letter with policy engine 236 or is mutual, so that confirm the checking and/or the mandate of long-distance user or remote client 102, makes that using transfer system 190 transmits one or more computing environment 15, application and/or data file.In yet another embodiment, equipment 200 is set up VPN or SSL VPN connection based on the checking and/or the mandate of 236 couples of long-distance users of policy engine or remote client 102.Among the embodiment, equipment 200 is based on the policy control network service traffic and the communication session of policy engine 236.For example, based on policy engine 236, equipment 200 may command are to the visit of computing environment 15, application or data file.

In certain embodiments, vServer 275 sets up transport layer with client computer 102 through client proxy 120 and is connected, and connects such as TCP or UDP.In one embodiment, vServer 275 monitorings and reception communicating by letter from client computer 102.In other embodiments, vServer 275 sets up transport layer with client-server 106 and is connected, and connects such as TCP or UDP.In one embodiment, vServer275 is established to the Internet protocol address of the server 270 that operates on the server 106 and the transport layer of port is connected.In yet another embodiment, vServer 275 will arrive the connection of first transport layer and the second transport layer join dependency couplet that arrives server 106 of client computer 102.In certain embodiments, vServer275 is established to the transport layer connection pool of server 106 and connects multiplexed client's request via the transport layer of said pondization (pooled).

In certain embodiments, equipment 200 provides the SSL VPN between client computer 102 and the server 106 to connect 280.For example, 102 requests of the client computer on first network 102 are established to the connection of the server 106 on second network 104 '.In certain embodiments, second network 104 ' can not be from first network, 104 routes.In other embodiments, client computer 102 is positioned on the common network 104, and server 106 is positioned on the dedicated network 104 ', for example enterprise network.In one embodiment, the communication of the client computer 102 on client proxy 120 interceptions first network 104 is encrypted and should be communicated by letter, and connects this equipment 200 of communicating by letter of transmission through first transport layer.Equipment 200 joins the second transport layer join dependency that first transport layer on first network 104 connects with server 106 to second network 104.The communication of being tackled that equipment 200 receives from client proxy 102, deciphering should be communicated by letter, and connected the server 106 that sends on this second network 104 of communicating by letter through second transport layer.It can be the transport layer connection of pondization that second transport layer connects.Same, equipment 200 is that two networks 104, the client computer between 104 ' 102 provide the End-to-End Security transport layer to connect.

In one embodiment, equipment 200 is posted the in-house network Internet protocol or IntranetIP (in-house network IP) 282 addresses of carrying the client computer 102 on the VPN 104.Client computer 102 has home network identifier, such as Internet protocol (IP) address and/or the Hostname on first network 104.When being connected to second network 104 ' through equipment 200, equipment 200 is gone up to client computer 102 at second network 104 ' and is set up, distributes or IntranetIP otherwise is provided, and it is the network identifier such as IP address and/or Hostname.Be used for the IntranetIP282 that is set up of client computer, equipment 200 second or private 104 ' on monitor and receive any communication of pointing to this client computer 102.In one embodiment, equipment 200 is used as or representative client 102 on second dedicated network 104.For example, In yet another embodiment, vServer 275 monitorings and the IntranetIP that responds client computer 102 282 communicate by letter.In certain embodiments, if the calculation element on second network 104 ' 100 sends request, equipment 200 is equally handled this request as client computer 102.For example, equipment 200 can respond the examination to client computer IntranetIP 282.In yet another embodiment, equipment can connect with the calculation element 100 on second network 104 that request is connected with client computer IntranetIP 282, connects such as TCP or UDP.

In certain embodiments, equipment 200 provides following one or more speed technology 288:1 for the communication between client computer 102 and the server 106) compression; 2) decompress; 3) transmission control protocol pond; 4) transmission control protocol is multiplexed; 5) transmission control protocol buffering; And 6) high-speed cache.In one embodiment; Equipment 200 connects allowing by the repeating data visit of client computer through the Internet through opening to be connected with one or more transport layer of each server 106 and to keep these, comes to alleviate a large amount of processing loads that caused to the transport layer connection of client computer 102 by the repetition opening and closing for server 106.This technology is called " connection pool " here.

In certain embodiments, in order to connect seamless spliced 106 the communication from client computer 102 to server through the transport layer of pondization, equipment 200 number is changed or multiplex communication with confirming through revise sequence number in the transport layer protocol level.This is called as " connecting multiplexed ".In certain embodiments, do not need application layer protocol to interact.For example, in the situation of the grouping that arrives (that is, from the grouping that client computer 102 receives), the source network address of said grouping is changed the network address into the output port of equipment 200, and the purpose network address is changed into the network address of destination server.Sending grouping (promptly; A grouping from server 106 receptions) in the situation; Source network address is changed into the network address of the output port of equipment 200 from the network address of server 106, and destination address is changed into the network address of the client computer 102 of request by the network address of slave unit 200.The sequence number that divides into groups and affirmation number also are converted into sequence number and the affirmation that client computer 102 that the transport layer of the equipment 200 of client computer 102 is connected is expected.In certain embodiments, the packet checks of transport layer protocol and quilt are recomputated to take into account these conversions.

In yet another embodiment, equipment 200 provides exchange or load balance function 284 for the communication between client computer 102 and the server 106.In certain embodiments, equipment 200 comes the distribution services amount and client requests is directed to server 106 according to layer 4 useful load or application-level request data.In one embodiment, although the network layer of network packet or layer 2 identifying purpose server 106, equipment 200 utilizes the data of the useful load that is carried as transport layer packet and application message to confirm server 106 so that distributed network divides into groups.In one embodiment, the health of health monitoring program 216 monitoring servers of equipment 200 confirms the distribution client requests is to which server 106.In certain embodiments, unavailable or have the load above predetermined threshold if equipment 200 detects certain server 106, equipment 200 can point to or be distributed to another server 106 with client requests.

In certain embodiments, equipment 200 perhaps otherwise provides parsing for the DNS request from client computer 102 as domain name service (DNS) resolver.In certain embodiments, the equipment interception is by the DNS request of client computer 102 transmissions.In one embodiment, equipment 200 is with IP address or its DNS request that comes the customer in response machine in the IP address of carrying of being posted of equipment 200.In this embodiment, client computer 102 sends to equipment 200 to the network service that is used for domain name.In yet another embodiment, equipment 200 with second equipment 200 ' or its DNS request that comes the customer in response machine in the IP address of carrying of being posted.In certain embodiments, equipment 200 uses the IP address of the server of being confirmed by equipment 200 106 to come the DNS request of customer in response machine.

In yet another embodiment, equipment 200 provides application firewall function 290 for the communication between client computer 102 and the server 106.In one embodiment, policy engine 236 is provided for surveying and blocking the rule of illegal request.In certain embodiments, application firewall 290 defence denials of service (DoS) are attacked.In other embodiments, the content of the request that equipment inspection is tackled is to discern and to block based on the attack of using.In certain embodiments, rule/policy engine 236 comprises one or more application firewall or the safety control strategy based on the protection of the tender spots of web or the Internet that is used to provide to a plurality of kinds and type, and for example following one or more tender spots: 1) buffer zone releases; 2) the CGI-BIN parameter is handled, and 3) list/hide field to handle 4) force to browse; 5) cookie or session poison 6) ruined ACL (ACLs) or weak password, 7) cross site scripting processing (XSS); 8) order injects 9) the SQL injection, 10) the erroneous trigger sensitive information leakage; 11) the dangerous use to encrypting, 12) the server error configuration, 13) back door and debugging option; 14) alter the website, and 15) platform or operating system weakness and 16) zero sky attack.In one embodiment; To one or more of scenario; Application firewall 290 provides the protection of html format field with the inspection or the form of phase-split network communication: 1) return required field, 2) do not allow added field, 3) read-only and hiding field enforcement (enforcement); 4) drop-down list and radio button field is consistent, and 5) the format fields length enforcement.In certain embodiments, application firewall 290 guarantees that cookie is not modified.In other embodiments, application firewall 290 defends to force to browse through carrying out legal URL.

In other embodiments, application firewall 290 is protected any confidential information that in network service, comprises.Application firewall 290 can be checked or analyzes arbitrary network service with the arbitrary confidential information in the either field that is identified in network packet according to the rule or the strategy of engine 236.In certain embodiments, application firewall 290 is discerned the one or many appearance at credit number, password, SSN, name, patient identification code, contact details and age in network service.The coded portion of network service can comprise these appearance or confidential information.Based on these appearance, in one embodiment, application firewall 290 can be taked the strategy action to network service, sends network service such as stoping.In yet another embodiment, application firewall 290 can rewrite, move or otherwise cover this appearance of discerning or confidential information.

Still with reference to figure 2B, equipment 200 can comprise the performance monitoring agency 197 who is discussed like top combination Fig. 1 D.In one embodiment, equipment 200 receives monitoring agent 197 from monitor service 198 described in Fig. 1 D or monitoring server 106.In certain embodiments, equipment 200 is preserved monitoring agent 197 in such as the memory storage of disk, to be used to send to any client computer or the server of communicating by letter with equipment 200.For example, in one embodiment, equipment 200 sends monitoring agent 197 when setting up the transport layer connection requests and gives client computer receiving.In other embodiments, equipment 200 sends monitoring agent 197 when foundation is connected with the transport layer of client computer 102.In yet another embodiment, equipment 200 sends monitoring agent 197 in interception or when detecting the request to the web page and gives client computer.In yet another embodiment, equipment 200 sends monitoring agent 197 to client computer or server in response to the request of monitoring server 198.In one embodiment, equipment 200 sends monitoring agents 197 to second equipment 200 ' or equipment 205.

In other embodiments, equipment 200 is carried out monitoring agent 197.In one embodiment, the performance of monitoring agent 197 measurements and monitoring any application, program, process, service, task or thread of execution on equipment 200.For example, performance and the operation of vServers 275A-275N can monitored and measure to monitoring agent 197.In yet another embodiment, monitoring agent 197 is measured the performance that is connected with any transport layer of watch-dog 200.In certain embodiments, the Any user performance of sessions through equipment 200 is measured and monitored to monitoring agent 197.In one embodiment, monitoring agent 197 is measured with any Virtual Private Network such as SSL VPN session of monitoring through equipment 200 and is connected and/or performance of sessions.In a further embodiment, internal memory, CPU and the disk of monitoring agent 197 measurements and watch-dog 200 use and performance.In yet another embodiment, the performance of any speed technology 288 of carrying out by equipment 200 of monitoring agent 197 measurements and monitoring such as SSL unloading, connection pool and multiplexed, high-speed cache and compression.In certain embodiments, monitoring agent 197 measurements and monitoring are by the arbitrary load balance of equipment 200 execution and/or the performance of content exchange 284.In other embodiments, monitoring agent 197 measurements and monitoring are by application firewall 290 protections and the processing performance of equipment 200 execution.

C. Client proxy

Refer now to Fig. 3, describe the embodiment of client proxy 120.Client computer 102 comprises client proxy 120, is used for setting up and switched communication via network 104 and equipment 200 and/or server 106.Generally speaking, client computer 102 is operated on calculation element 100, and this calculation element 100 has the operating system that has kernel mode 302 and user model 303, and the network stack 310 that has one or more layers of 310a-310b.One or more application can installed and/or carry out to client computer 102.In certain embodiments, one or more application can be communicated by letter with network 104 through network stack 310.One of said application such as the web browser, also can comprise first program 322.For example, can use first program 322 to install and/or carry out client proxy 120 in certain embodiments, or any part wherein.Client proxy 120 comprises interception mechanism or blocker 350, is used for from the network service of network stack 310 interceptions from one or more application.

The network stack 310 of client computer 102 can comprise software or hardware or its combination of any kind and form, is used to provide and being connected and communicating by letter of network.In one embodiment, network stack 310 comprises the software realization that is used for network protocol suite.Network stack 310 can comprise one or more network layers, for example is any network layer of the open system interconnection (osi) traffic model that those skilled in the art generally acknowledged and understood.Like this, network stack 310 can comprise any kind that is used for any following osi model layer and the agreement of form: 1) physical link layer; 2) data link layer; 3) network layer; 4) transport layer; 5) session layer); 6) presentation layer, and 7) application layer.In one embodiment, network stack 310 can be included in the transmission control protocol (TCP) on the network layer protocol of Internet Protocol (IP), is commonly referred to TCP/IP.In certain embodiments, can on Ethernet protocol, carry ICP/IP protocol, Ethernet protocol can comprise any family of IEEE wide area network (WAN) or Local Area Network agreement, these agreements that for example covered by IEEE802.3.In certain embodiments, network stack 310 comprises the wireless protocols of any kind and form, for example IEEE802.11 and/or mobile Internet Protocol.

Consideration is based on the network of TCP/IP; Can use any agreement based on TCP/IP; Comprise messages application DLL (MAPI) (email), FTP (FTP), HTTP(Hypertext Transport Protocol), common internet file system (CIFS) agreement (file transfer), independent computing architecture (ICA) agreement, RDP (RDP), wireless application protocol (wap), mobile IP protocol, and ip voice (VoIP) agreement.In yet another embodiment; Network stack 310 comprises the transmission control protocol of any kind and form, such as the transmission control protocol of revising, for example affairs TCP (T/TCP); Have the TCP (TCP-SACK) that selects affirmation; The TCP (TCP-LW) that has big window, the for example congestion prediction agreement of TCP-Vegas agreement, and TCP fraud protocol.In other embodiments, network stack 310 can use such as IP and go up any kind of UDP and the UDP (UDP) of form, for example is used for voice communication or real-time data communication.

In addition, network stack 310 can comprise one or more network drives of one or more layers of supports, for example TCP driver or network layer driver.The part that the network layer driver can be used as the operating system of calculation element 100 is perhaps comprised as any NIC of calculation element 100 or the part of other access to netwoks assembly.In certain embodiments, any network drive of network stack 310 can be used for supporting any technology described herein by customization, modification or adjustment customization or the modification part so that network stack 310 to be provided.In other embodiments, design and make up accelerated procedure 302 with network stack 310 co-operatings or work, above-mentioned network stack 310 is by the operating system installation of client computer 102 or otherwise provide.

Network stack 310 comprises the interface of any kind and form, is used to receive, obtain, provide or otherwise visit any information and the data of the network service that relates to client computer 102.In one embodiment, the interface with network stack 310 comprises API (API).Interface also can comprise any function call, hook or strobe utility, the interfacing of incident or callback mechanism or any kind.Network stack 310 can receive or provide and the function of network stack 310 or relevant any kind and the data structure of form, the for example object of operation through interface.For example, data structure can comprise the information relevant with network packet and data or one or more network packet.In certain embodiments, data structure is included in the part of the network packet that the protocol layer of network stack 310 handles, the for example network packet of transport layer.In certain embodiments, data structure 325 comprises kernel rank data structure, and in other embodiments, data structure 325 comprises the user model data structure.Kernel-level data can comprise data structure acquisition or relevant with the part of network operating storehouse 310 in kernel mode 302, or operate in network driver or other software in the kernel mode 302, or by operation or operate in any data structure that service, process, task, thread or other executable instruction of the kernel mode of operating system obtain or receive.

In addition, the some parts of network stack 310 can be carried out or operation at kernel mode 302, for example, and data link or network layer, and other parts are in user model 303 execution or operation, the for example application layer of network stack 310.For example, the 310a of first of network stack can provide the user model visit to network stack 310 to application, and the second portion 310a of network stack 310 provides the visit to network.In certain embodiments, the 310a of first of network stack can comprise one or more more upper stratas of network stack 310, for example any layer of layer 5-7.In other embodiments, the second portion 310b of network stack 310 comprises one or more lower layers, for example any layer of layer 1-4.Any part that each 310a of first of network stack 310 and second portion 310b can comprise network stack 310; Be positioned at any one or a plurality of network layer; Be in user model 203, kernel mode 202; Or its combination, or in any part of network layer or to the point of interface of network layer, or any part of user model 203 and kernel mode 202 or to the point of interface of user model 203 and kernel mode 202.

Blocker 350 can comprise any combination of software, hardware or software and hardware.In one embodiment, blocker 350 is in any point of network stack 310 interception network service, and is redirected or sends the destinations of network service to or control desired, management by blocker 350 or client proxy 120.For example, blocker 350 can be tackled the network service of the first network of network storehouse 310 and send this network service to equipment 200, is used on second network 104, sending.In certain embodiments, blocker 350 comprises the blocker 350 that contains such as arbitrary type of the driver that is fabricated and designs the next network drive that docks with network stack 310 and work together.In certain embodiments, client proxy 120 and/or blocker 350 operate in one or more layer of network stack 310, such as in transport layer.In one embodiment, blocker 350 comprises filter driver, Hook Mechanism, or is connected to arbitrary form and the suitable networks driver interface of type of the transport layer of network stack, such as through transfer driver interface (TDI).In certain embodiments, blocker 350 is connected to such as first protocol layer of transport layer with such as another protocol layer of any layer on the transmission protocol layer, for example, and application protocol layer.In one embodiment, blocker 350 can comprise the driver of observing NetWare Driver Interface Specification (NDIS), perhaps ndis driver.In yet another embodiment, blocker 350 can comprise microfilter or little port driver.In one embodiment, blocker 350 or its part are operated in kernel mode 202.In yet another embodiment, blocker 350 or its part are operated in user model 203.In certain embodiments, the part of blocker 350 is operated in kernel mode 202, and another part of blocker 350 is operated in user model 203.In other embodiments, client proxy 120 is in user model 203 operation, but is connected to the part of kernel mode driver, process, service, task or operating system through blocker 350, such as to obtain kernel-level data 225.In other embodiments, blocker 350 is user mode application or program, such as application.

In one embodiment, any transport layer connection request of blocker 350 interceptions.In these embodiment, blocker 350 is carried out transport layer API (API) and is called so that destination information to be set, and is used for the location such as IP address, destination and/or port to the expectation position.In this way, blocker 350 is tackled the directional transmissions layer of laying equal stress on and is connected to IP address and port by blocker 350 or client proxy 120 controls or management.In one embodiment, blocker 350 is purpose of connecting ground information setting the local ip address and the port of the client computer 102 of client proxy 120 monitorings.For example, client proxy 120 can be included as the redirected transport layer communication intercept local ip address and the agency service of port.In certain embodiments, client proxy 120 is sent to equipment 200 with the transport layer communication that is redirected subsequently.

In certain embodiments, blocker 350 interception domain name service (DNS) requests.In one embodiment, client proxy 120 and/or blocker 350 are resolved the DNS request.In yet another embodiment, blocker sends the DNS tackled and asks equipment 200 to carry out dns resolution.In one embodiment, equipment 200 is resolved the DNS request and the DNS response is sent to client proxy 120.In certain embodiments, equipment 200 is resolved the DNS request through another equipment 200 ' or dns server 106.

In yet another embodiment, client proxy 120 can comprise two

agencies

120 and 120 '.In one embodiment, first agency 120 can be included in the blocker 350 of the network layer operation of network stack 310.In certain embodiments, first agency, 120 interception network layer requests are such as Internet Control Message Protocol (ICMP) request (for example, examination and traceroute).In other embodiments, second agency 120 ' can be in transport layer operations and the communication of interception transport layer.In certain embodiments, first agency 120 is connected in one deck interception communication of network stack 210 and with second agency 120 ' or the communication of being tackled is sent to second agency 120 '.

Client proxy 120 and/or blocker 350 can be operated or butt joint with it at protocol layer with any other protocol layer transparent way to network stack 310.For example; In one embodiment, blocker 350 can with to such as any protocol layer under the transport layer of network layer and such as any protocol layer transparent way on the transport layer of session, expression or application layer protocol the transport layer operations of network stack 310 or with it the butt joint.This allows other protocol layer of network stack 310 such as desired operating and need not to revise to use blocker 350.Like this, client proxy 120 and/or blocker 350 can be connected arbitrary communication that arbitrary agreement of carrying via transport layer with safety, optimization, acceleration, route or load balance provides with transport layer, such as the arbitrary application layer protocol on the TCP/IP.

In addition, client proxy 120 and/or blocker can be operated on network stack 310 with any other calculation element transparent way such as server of communicating by letter with client computer 102 with the user to any application, client computer 102 or butt joint with it.Client proxy 120 and/or blocker 350 can be mounted and/or carry out on client computer 102 with the mode that need not to revise application.In certain embodiments, the user of client computer 102 or the calculation element of communicate by letter with client computer 102 do not recognize client proxy 120 and/or blocker 350 existence, carry out or operate.Equally; In certain embodiments, with respect to use, the user of client computer 102, such as another calculation element of server, or on the protocol layer that connects by blocker 350 and/or under any protocol layer install, carry out and/or operate client proxy 120 and/or blocker 350 pellucidly.

Client proxy 120 comprises accelerated procedure 302, stream client computer 306, collects agency 304 and/or monitoring agent 197.In one embodiment, client proxy 120 comprises independent computing architecture (ICA) client computer or its arbitrary part by the Citrix Systems Inc. exploitation of Florida State Fort Lauderdale, and also refers to the ICA client computer.In certain embodiments, client proxy 120 comprises application flow client computer 306, is used for being applied to client computer 102 from server 106 stream transmissions.In certain embodiments, client proxy 120 comprises accelerated procedure 302, is used to quicken the communication between client computer 102 and the server 106.In yet another embodiment, client proxy 120 comprises collects agency 304, is used to carry out end-point detection/scan and be used to equipment 200 and/or server 106 collecting terminal dot informations.

In certain embodiments; Accelerated procedure 302 comprises the client-side accelerated procedure that is used to carry out one or more speed technologies; With quicken, strengthen or otherwise improve client computer and server 106 communicate by letter and/or to the visit of server 106, such as visiting the application that provides by server 106.The logic of the executable instruction of accelerated procedure 302, function and/or operation can be carried out one or more following speed technologies: 1) multi-protocols compression; 2) transmission control protocol pond; 3) transmission control protocol is multiplexed; 4) transmission control protocol buffering, and the 5) high-speed cache through cache manger.In addition, accelerated procedure 302 can be carried out the encryption and/or the deciphering of any communication that is received and/or sent by client computer 102.In certain embodiments, accelerated procedure 302 is carried out one or more speed technology with integrated mode or form.In addition, accelerated procedure 302 can be carried out compression to the arbitrary agreement or the multi-protocols of carrying as the useful load of the network packet of transport layer protocol.

Stream client computer 306 comprises application, program, process, service, task or executable instruction, and said application, program, process, service, task or executable instruction are used to receive and carry out the application of being transmitted as a stream from server 106.Server 106 can be transmitted one or more application data file as a stream to stream client computer 306, is used to play, carry out or causes that otherwise the application on the client computer 102 is performed.In certain embodiments, server 106 sends one group of application data file of compressing or packing to stream client computer 306.In certain embodiments, a plurality of application files are compressed and are stored on the file server in the files, for example CAB, ZIP, SIT, TAR, JAR or out file.In one embodiment, server 106 decompresses, unpacks or separate grade application file and this document is sent to client computer 102.In yet another embodiment, client computer 102 decompresses, unpacks or separate a grade application file.Stream client computer 306 dynamic installation application or its parts, and carry out and should use.In one embodiment, stream client computer 306 can be executable program.In certain embodiments, stream client computer 306 can start another executable program.

Collect agency 304 and comprise application, program, process, service, task or executable instruction, be used to discern, obtain and/or collect information about client computer 102.In certain embodiments, equipment 200 sends and collects agency 304 to client computer 102 or client proxy 120.Can dispose according to one or more strategies of the policy engine 236 of equipment and collect agency 304.In other embodiments, collection agency 304 is sent in the information of collecting on the client computer 102 and arrives equipment 200.In one embodiment, the policy engine 236 of equipment 200 uses collected information to confirm and the visit that be connected of client computer to network 104, authentication vs. authorization control is provided.

In one embodiment, collect agency 304 and comprise end-point detection and scan mechanism, one or more attribute or the characteristic of its identification and definite client computer.For example, collect agency 304 can discern and confirm any one or a plurality of below the client-side attribute: the 1) version of operating system and/or operating system, 2) services package of operating system, 3) service of operation, 4) process and 5 moved) file.Collect that agency 304 can also discern and definite client computer on the existence or the version of any one or more following softwares: 1) anti-virus software; 2) personal firewall software; 3) internet security software Anti-Spam software and 4).Policy engine 236 can have based on any one of client computer or client-side attribute or one or more strategies of a plurality of attribute or characteristic.

In certain embodiments, client proxy 120 comprises the monitoring agent 197 as combining Fig. 1 D and 2B to be discussed.Monitoring agent 197 can be such as any kind of Visual Basic or java script and the script of form.In one embodiment, the performance of monitoring agent 197 monitoring and measuring customer machine agency's 120 any part.For example, in certain embodiments, the performance of monitoring agent 197 monitoring and measurement accelerated procedure 302.In yet another embodiment, the performance of monitoring agent 197 monitoring and measurement stream client computer 306.In other embodiments, monitoring agent 197 monitoring and measurement collection agency's 304 performance.In yet another embodiment, the performance of monitoring agent 197 monitoring and measurement blocker 350.In certain embodiments, any resource such as storer, CPU and disk of monitoring agent 197 monitoring and measuring customer machine 102.

Monitoring agent 197 can be monitored the performance with any application of measuring customer machine.In one embodiment, the performance of the browser on monitoring agent 197 monitoring and the measuring customer machine 102.In certain embodiments, monitoring agent 197 monitoring and measurement are via the performance of any application of client proxy 120 transmission.In other embodiments, final user's response time that monitoring agent 197 is measured and monitoring is used is for example based on response time or http response time of web.The performance of ICA or RDP client computer can monitored and measure to monitoring agent 197.In yet another embodiment, the index of monitoring agent 197 measurements and supervisory user session or utility cession.In certain embodiments, monitoring agent 197 is measured and monitoring ICA or RDP session.In one embodiment, monitoring agent 197 is measured with watch-dog 200 and is being quickened to transmit application and/or the data performance in the process of client computer 102.

In certain embodiments, still with reference to figure 3, the first programs 322 can be used for automatically, mourn in silence ground, install and/or carry out client proxy 120 or its part pellucidly or otherwise, such as blocker 350.In one embodiment, first program 322 comprises plug in component, for example ActiveX control or Java control or script, and it is loaded into uses and carries out by using.For example, first program comprises the ActiveX control that is written into and is moved by the web browser application, for example in the context of storage space or application.In yet another embodiment, first program 322 comprises executable instruction sets, and this executable instruction sets is written into and carries out by the for example application of browser.In one embodiment, first program 322 comprises that the program that is designed and constructs is to install client proxy 120.In certain embodiments, first program 322 obtains, downloads or subscribing client agency 120 from another calculation element through network.In yet another embodiment, first program 322 is to be used on the operating system of client computer 102, installing installation procedure or the plug and play manager like the program of network-driven.

D. Be used to provide the system and method for virtualization applications transfer control

Refer now to Fig. 4 A, block diagram is described an embodiment of virtualized environment 400.In general, calculation element 100 comprises supervisory routine layer, virtualization layer and hardware layer.The supervisory routine layer comprises supervisory routine 401 (being also referred to as the virtual management device), and it distributes through at least one virtual machine of in virtualization layer, carrying out and manages visit to a plurality of physical resources in the hardware layer (for example processor 421 and disk 428).Virtualization layer comprises at least one operating system 410 and a plurality of virtual resources of distributing at least one operating system 410.Virtual resource can include, without being limited to a plurality of

virtual processor

432a, 432b, 432c (being generically and collectively referred to as 432) and

virtual disk

442a, 442b, 442c (being generically and collectively referred to as 442), and like the virtual resource of virtual memory and virtual network interface.Can a plurality of virtual resources and operating system be called virtual machine 406.Virtual machine 406 can comprise control operation system 405, and this control operation system 405 communicates by letter with supervisory routine 401, and is used to carry out application with other virtual machines on management and the configuration calculation element 100.

Particularly, supervisory routine 401 can provide virtual resource to operating system with any way of the operating system of simulating addressable physical equipment.Supervisory routine 401 can provide virtual resource to arbitrary quantity

client operating system

410a, 410b (being generically and collectively referred to as 410).Among some embodiment, calculation element 100 is carried out one or more supervisory routines.Among these embodiment, supervisory routine can be used for simulating virtual hardware, division physical hardware, virtual physical hardware and carries out provides the virtual machine to the visit of computing environment.Supervisory routine can comprise these programs by the VMWare manufacturing of the Palo Alto that is positioned at California, USA; XEN supervisory routine (a kind of product of increasing income, its exploitation is by the Xen.org association supervision of increasing income); The HyperV, VirtualServer or the Virtual PC supervisory routine that provide by Microsoft, or other.Among some embodiment, calculation element 100 is carried out and is created the supervisory routine that client operating system can be carried out virtual machine platform above that, and this calculation element 100 is called as home server.In of these embodiment, for example, calculation element 100 is the XEN SERVER that provided by the Citrix Systems company that is positioned at Fla. Fort Lauderdale.

Among some embodiment, supervisory routine 401 is carried out within the operating system of carrying out on the calculation element.In of these embodiment; The calculation element of executive operating system and supervisory routine 401 can be regarded as has host operating system (carrying out the operating system on calculation element), and client operating system (operating system of in the computational resource subregion that is provided by supervisory routine 401, carrying out).Among other embodiment, supervisory routine 401 is directly mutual rather than on host operating system, carry out with the hardware on the calculation element.In of these embodiment, supervisory routine 401 can be regarded as at " naked metal (bare metal) " and go up execution, and said " naked metal " refers to comprise the hardware of calculation element.

Among some embodiment, supervisory routine 401 can produce the virtual machine 406a-c (being generically and collectively referred to as 406) that operating system 410 is carried out therein.In of these embodiment, supervisory routine 401 loaded virtual machine reflection is to create virtual machine 406.In another of these embodiment, supervisory routine 401 is executive operating system 410 in virtual machine 406.Still in another of these embodiment, virtual machine 406 executive operating systems 410.

Among some embodiment, supervisory routine 401 is controlled at the processor scheduling and the internal memory of the virtual machine of carrying out on the calculation element 100 406 and divides.In of these embodiment, the execution of supervisory routine 401 at least one virtual machine 406 of control.In another of these embodiment, supervisory routine 401 presents the abstract of at least one hardware resource of being provided by calculation element 100 at least one virtual machine 406.Among other embodiment, whether and how supervisory routine 401 controls present to virtual machine 406 with the concurrent physical processor ability.

Control operation system 405 can carry out at least one application that is used to manage and dispose client operating system.Among the embodiment; Control operation system 405 can carry out management application; As comprise the application of following user interface; This user interface provides the visit to the function that is used for the managing virtual machines execution for the keeper, and these functions comprise the function that is used to carry out virtual machine, the execution of termination virtual machine or discerns the physical resource type that will distribute to virtual machine.Among another embodiment, supervisory routine 401 is executivecontrol function system 405 in the virtual machine of being created by supervisory routine 401 406.Among another embodiment, control operation system 405 carries out being authorized to directly to visit on the virtual machine 406 of the physical resource on the calculation element 100.Among some embodiment, the 405a of control operation system on the calculation element 100a can be through communication between supervisory routine 401a and the supervisory routine 401b and the 405b of the control operation system swap data on the calculation element 100b.Like this, one or more calculation element 100 can with the data of available other physical resources in one or more other calculation elements 100 relevant processors of exchange or the resource pool.In of these embodiment, this function allows the supervisory routine management to be distributed in the resource pool on a plurality of physical compute devices.In another of these embodiment, one or more client operating systems that a plurality of supervisory routines management are carried out on a calculation element 100.

Among the embodiment, control operation system 405 be authorized to the mutual virtual machine 406 of at least one client operating system 410 on carry out.Among another embodiment, client operating system 410 is communicated by letter with control operation system 405 through supervisory routine 401, with request visit disk or network.Still In yet another embodiment, client operating system 410 can be communicated by letter through the communication channel of being set up by supervisory routine 401 with control operation system 405, for example, and through a plurality of shared storage pages that provide by supervisory routine 401.

Among some embodiment, control operation system 405 comprises and is used for the network back driver of directly communicating by letter with the network hardware that is provided by calculation element 100.In of these embodiment, the network back driver is handled at least one the virtual machine request from least one client operating system 110.Among other embodiment, control operation system 405 comprise be used for calculation element 100 on the memory element piece back driver of communicating by letter.In of these embodiment, the piece back driver reads and writes data from memory element based at least one request that receives from client operating system 410.

An embodiment, control operation system 405 comprises instrument storehouse 404.Among other embodiment, instrument storehouse 404 provides following function: communicate by letter with other control operation systems 405 (for example being positioned on the second calculation element 100b) alternately with supervisory routine 401, perhaps virtual machine 406b, the 406c on the Management Calculation device 100.Among another embodiment, instrument storehouse 404 comprises self-defined application, and it is used for to the keeper of a virtual group of planes improved management function being provided.Among some embodiment, at least one in instrument storehouse 404 and the control operation system 405 comprises Administration API, and it is provided for Remote configuration and controls the interface of the virtual machine 406 of operation on the calculation element 100.Among other embodiment, control operation system 405 communicates by letter with supervisory routine 401 through instrument storehouse 404.

Among the embodiment, supervisory routine 401 is carried out client operating system 410 in the virtual machine of being created by supervisory routine 401 406.Among another embodiment, client operating system 410 provides the visit to the resource in the computing environment for the user of calculation element 100.Among another embodiment, resource comprises program, application, document, file, a plurality of application, a plurality of file, executable program file, desktop environment, computing environment or other resources that can use the user of calculation element 100.Among another embodiment; Can send resource to calculation element 100 through a plurality of access methods, these methods include but not limited to: conventional directly install on the calculation element 100, method through application flow sends calculation element 100 to, will by second calculation element 100 ' on carry out output data that resource produces and send calculation element 100 to through presentation level protocol send to calculation element 100, will through second calculation element 100 ' on the virtual machine carried out carry out output data that resource produced and send calculation element 100 to, or carry out or carry out and produce output data through the virtual machine of carrying out at calculation element 100 from the flash memory device (for example USB device) that is connected to calculation element 100.Among some embodiment, calculation element 100 will carry out output data that resource produces be transferred to another calculation element 100 '.

Among the embodiment; Client operating system 410 combines form complete virtual virtual machine with the virtual machine that this client operating system 410 is carried out above that; This complete virtual virtual machine does not also know it oneself is virtual machine, and such machine can be described as " Domain U HVM (hardware virtual machine) virtual machine ".Among another embodiment, complete virtual machine comprise the simulation basic input/output (BIOS) software in case in complete virtual machine executive operating system.In yet another embodiment, complete virtual machine can comprise driver, and it provides function through communicating by letter with supervisory routine 401.Among such embodiment, driver can be recognized and own in virtualized environment, carries out.Among another embodiment; Client operating system 410 combines form ultra virtual (paravirtualized) virtual machine with the virtual machine that this client operating system 410 is carried out above that; This ultra virtual virtual machine recognizes it oneself is virtual machine, and such machine can be described as " Domain U PV virtual machine ".Among another embodiment, ultra virtual machine comprises complete virtual machine extra driver not to be covered.Among another embodiment, ultra virtual machine comprises aforesaid network back driver and the piece back driver that is comprised in the control operation system 405.

Refer now to Fig. 4 B, block diagram has been described an embodiment of a plurality of networking calculation elements in the system, and wherein, at least one physical host is carried out virtual machine.In general, system comprises Management Unit 404 and supervisory routine 401.System comprises a plurality of calculation element 100, a plurality of virtual machine 406, a plurality of supervisory routine 401, a plurality of Management Unit (being called instrument storehouse 404 or Management Unit 404 again) and physical resource 421,428.Each of a plurality of physical machines 100 can be provided as as above combining the calculation element 100 of Fig. 1 E-1H and Fig. 4 A description.

Particularly, physical disk 428 is provided by calculation element 100, storage at least a portion virtual disk 442.Among some embodiment, virtual disk 442 is associated with a plurality of physical disks 428.In of these embodiment; One or more calculation elements 100 can exchange the data of other available in relevant processors or resource pool physical resources with one or more other calculation elements 100, allow the supervisory routine management to be distributed in the resource pool on a plurality of physical compute devices.Among some embodiment, the calculation element 100 that virtual machine 406 is carried out above that is called physical host 100 or main frame 100.

Supervisory routine is carried out on the processor on the calculation element 100.Supervisory routine will be distributed to virtual disk to the visit capacity of physical disk.Among the embodiment, the amount of space that supervisory routine 401 is distributed on the physical disk.Among another embodiment, a plurality of pages that supervisory routine 401 is distributed on the physical disk.Among some embodiment, supervisory routine provides virtual disk 442 as an initialization and a part of carrying out virtual machine 450 processes.

Among the embodiment, Management Unit 404a is called pond Management Unit 404a.Among another embodiment, the MOS 405a that can be called control management system 405a comprises Management Unit.Among some embodiment, Management Unit is called the instrument storehouse.In of these embodiment, Management Unit is the instrument storehouse 404 that preceding text combine Fig. 4 A to describe.Among other embodiment, Management Unit 404 provides user interface, is used for from receive the sign of the virtual machine 406 that will supply and/or carry out like keeper's user.Still in other embodiments, Management Unit 404 provides user interface, is used for receiving the request of virtual machine 406b being moved to another physical machine from a physical machine 100 from the user like the keeper.In a further embodiment; Management Unit 404a identification is carried out the calculation element 100b of the virtual machine 406d that is asked above that and is indicated the supervisory routine 401b on the calculation element 100b that is discerned to carry out the virtual machine of being discerned; Like this, can Management Unit be called the pond Management Unit.

Refer now to Fig. 4 C, described the embodiment of virtual application transfer control or virtual unit 450.In general, preceding text combine any function and/or the embodiment (for example using transfer control) of the equipment 200 that Fig. 2 A and 2B describe can be deployed among any embodiment of virtualized environment that preceding text combine Fig. 4 A and 4B description.The function of using transfer control is not to dispose with the form of equipment 200, but with this function distributing in such as the virtualized environment 400 on any calculation element 100 of client computer 102, server 106 or equipment 200.

With reference now to Fig. 4 C,, the block diagram of the embodiment of the virtual unit 450 of operation on the supervisory routine 401 of server 106 has been described.Equipment 200 like Fig. 2 A and 2B is the same, and virtual machine 450 can provide availability, performance, unloading and safe functioning.For availability, virtual unit can be carried out the load balance between the 4th layer and the 7th layer on the network and carry out intelligence service health monitoring.Performance for quickening through Network to realize increases, and virtual unit can be carried out buffer memory and compression.Unloading for any server is handled, and virtual unit can be carried out connection multiplexing and connection pool and/or SSL and handle.For safety, any application firewall function and SSL VPN function that virtual unit can actuating equipment 200.

Any module of the equipment of describing in conjunction with accompanying drawing 2A 200 can virtual equipment transfer control 450 form packed, made up, designed or constructed, virtual equipment transfer control 450 can be deployed to software module or the assembly of carrying out in virtualized environment 300 or the non-virtualized environment on any server such such as popular server.The form that for example, can be installed in the installation kit on the calculation element provides virtual unit.With reference to figure 2A, can with any design in cache manger 232, policy engine 236, compression 238, crypto engine 234, Packet engine 240, GUI 210, CLI 212, the shell service 214 and be formed in calculation element and/or any operating system of virtualized environment 300 on assembly or the module moved.Virtual equipment 400 does not use encryption processor 260, processor 262, storer 264 and the network stack 267 of equipment 200, but can use these otherwise available resources on any of these resource that virtualized environment 400 provides or the server 106.

Still with reference to figure 4C, in brief, any one or a plurality of vServer 275A-275N can operate or carry out in the virtualized environment 400 of the calculation element 100 (like server 106) at any type.Any module and the function of the equipment of describing in conjunction with accompanying drawing 2B 200 can design and be configured in the virtual or non-virtualized environment of server, to operate.Can in vServer 275, SSL VPN 280, Intranet UP 282, switch 284, DNS 286, accelerator 288, APP FW 280 and the monitoring agent any be packed, makes up, designs or be configured to use the form of transfer control 450, use transfer control 450 and can be deployed to one or more software modules or the assembly of in device and/or virtualized environment 400, carrying out.

Among some embodiment, server can be carried out a plurality of virtual machine 406a-406b in virtualized environment, the identical or different embodiment of each virtual machine operation virtual application transfer control 450.Among some embodiment, server can be at one or more virtual units 450 of carrying out on the nuclear of multiple core processing system on one or more virtual machines.Among some embodiment, server can be at one or more virtual units 450 of carrying out on each processor of multiprocessor device on one or more virtual machines.

E. The system and method for multicore architecture is provided

According to Moore's Law, every two years installable transistorized quantity can be double basically on the integrated circuit.Yet the increase of CPU speed can reach a stable level (plateaus), and for example, since 2005, CPU speed is in the scope of about 3.5-4GHz.Under the certain situation, CPU manufacturer possibly not rely on the increase of CPU speed to obtain extra performance.Number of C PU manufacturer can increase additional nuclear so that extra performance to be provided to processor.The product like software and Network Provider that relies on the CPU obtained performance to improve can improve their performance through utilizing these multi-core CPUs.The software that can design and/or be written as single CPU design and structure again is to utilize multithreading, parallel architecture or multicore architecture.

Among some embodiment, the multicore architecture permission equipment that is called the equipment 200 of nCore or multi-core technology is broken the monokaryon performance penalty and is utilized the ability of multi-core CPU.Preamble combines in the framework of Fig. 2 A description, operation single network or Packet engine.The multinuclear of nCore technology and framework allows simultaneously and/or moves concurrently a plurality of Packet engine.Through on each nuclear, moving Packet engine, the processing power of the additional nuclear of equipment framework utilization.Among some embodiment, this provides performance improvement and extendability up to seven times.

Fig. 5 A illustrate according to one type of parallel mechanism or parallel computation scheme (as function parallelization mechanism, data parallel is machine-processed or based on the data parallel mechanism of stream) some embodiment of the work, task, load or the Network that on one or more processor cores, distribute.In general, Fig. 5 A illustrate as the equipment 200 with n nuclear ' the embodiment of multiple nucleus system, n nuclear is numbered 1 and arrives N.Among the embodiment; Work, load or Network can be distributed on the first nuclear 505A, the second nuclear 505B, the 3rd nuclear 505C, the 4th nuclear 505D, the 5th nuclear 505E, the 6th nuclear 505F, the 7th nuclear 505G etc.; Like this, distribute and to be arranged on all n nuclear 505N (after this being referred to as nuclear 505) or n examine two or more.A plurality of VIP 275 can be arranged, and each operates on the corresponding nuclear of a plurality of nuclears.A plurality of Packet engine 240 can be arranged, and each operates in the corresponding nuclear of a plurality of nuclears.Any method of using can produce different, that change or similar operating load or the performance class 515 on arbitrary nuclear in a plurality of nuclears.For the function parallelization method, each nuclear moves the difference in functionality of a plurality of functions that provided by Packet engine, VIP 275 or equipment 200.In the data parallel method, data are can be based on the NIC (NIC) that receives data or VIP 275 parallel or be distributed on the nuclear.In another data parallel method, can go up and processing is distributed on the nuclear through data stream being distributed in each nuclear.

In the further details of Fig. 5 A, among some embodiment, can load, work or Network be distributed on the nuclear 505 according to function parallelization mechanism 500.Function parallelization mechanism can be based on each nuclear of carrying out one or more corresponding functions.Among some embodiment, first endorses execution first function, and second nuclear is carried out second function simultaneously.In the function parallelization method, divide and be distributed to each nuclear according to the functional function that multiple nucleus system will be carried out.Among some embodiment, can function parallelization mechanism be called tasks in parallel mechanism, and can or check same data or different pieces of information realizes when carrying out different processes or function at each processor.Nuclear or processor can be carried out identical or different code.Under the certain situation, different execution threads or code can intercom when work mutually.Can communicate so that data are passed to next thread as the part of workflow from a thread.

Among some embodiment; According to function parallelization mechanism 500 work is distributed on the nuclear 505; Can comprise that said specific function for example is network incoming/outgoing management (NWI/O) 510A, secure socket layer (ssl) encryption and decryption 510B and transmission control protocol (TCP) function 510C according to specific function distributed network business.This can produce based on the work of employed function or functional class, performance or computational load 515.Among some embodiment, according to data parallel mechanism 540 work is distributed in and comprises on the nuclear 505 based on the distributed data that is associated with specific hardware or the component software workload 515 that distributes.Among some embodiment, can comprise on the nuclear 505 based on context or stream and come distributed data according to work being distributed in, thereby make the workload 515A-N on each nuclear similarly, basic to equate or to be evenly distributed relatively based on the data parallel mechanism 520 of stream.

Under the situation of function parallelization method, can dispose each and examine one or more functions of moving in a plurality of functions that Packet engine or VIP by equipment provide.For example, but the network I/O of nuclear 1 actuating equipment 200 ' handle, examine the TCP connection management of 2 actuating equipments simultaneously.Similarly, nuclear 3 can be carried out the SSL unloading, examines 4 simultaneously and can carry out the 7th layer or application layer process and service management.Each is endorsed and carries out identical or different function.Each endorses not only function of execution.Arbitrary endorsing moved function or its part that combines accompanying drawing 2A and 2B identification and/or description.In this method, the work on the nuclear can coarseness or the fine granularity mode divide by function.Under the certain situation, shown in Fig. 5 A, can make different IPs operate in different performances or load level 515 by the function division.

Under the situation of function parallelization method, can dispose each and examine one or more functions of moving in a plurality of functions that the Packet engine by equipment provides.For example, but the network I/O of nuclear 1 actuating equipment 200 ' handle, examine the TCP connection management of 2 actuating equipments simultaneously.Similarly, nuclear 3 can be carried out the SSL unloading, examines 4 simultaneously and can carry out the 7th layer or application layer process and service management.Each is endorsed and carries out identical or different function.Each endorses not only function of execution.Any endorsing moved function or its part that combines accompanying drawing 2A and 2B identification and/or description.In this method, the work on the nuclear can coarseness or the fine granularity mode divide by function.Under the certain situation, shown in Fig. 5 A, can make different IPs operate in different performances or load level by the function division.

Can come distributed function or task with any structure or scheme.For example, Fig. 5 B illustrates the first nuclear Core1 505A that is used to handle the application that is associated with network I/O function 510A and process.Among some embodiment, the Network that is associated with network I/O can be associated with specific port numbers.Thereby the grouping of sending and arriving that will have the port destination that is associated with NW I/O 510A is guided to Core1505A, and this Core1 505A is exclusively used in the all-network business that is associated with NW I/O port of handling.Similarly, Core2 505B is exclusively used in to handle with SSL and handles the function that is associated, and Core4 505D can be exclusively used in and handle all processing of TCP levels and functions.

Though Fig. 5 A illustrates the function like network I/O, SSL and TCP, also can other functions be distributed to nuclear.These other functions can comprise arbitrary or a plurality of function described herein or operation.For example, any function in conjunction with Fig. 2 A and 2B description can be distributed on the nuclear based on the function basis.Under the certain situation, a VIP275A may operate on first nuclear, and simultaneously, the 2nd VIP 275B with different configurations may operate on second nuclear.Among some embodiment, each nuclear 505 can be handled specific function, and each nuclear 505 can be handled the processing that is associated with this specific function like this.For example, but Core 2505B treatment S SL unloading, and Core4 505D can handle application layer process and service management simultaneously.

Among other embodiment, can work, load or Network be distributed on the nuclear 505 according to the data parallel mechanism 540 of any kind or form.Among some embodiment, can realize the data parallel mechanism in the multiple nucleus system by each different sheets execution same task or function of checking distributed data.Among some embodiment, single execution thread or code control are to the operation of all data slice.Among other embodiment, different threads or instruction control operation, but can carry out same code.Among some embodiment, realize data parallel mechanism from Packet engine, vServer (VIP) 275A-C, NIC (NIC) 542D-E and/or equipment 200 any other network hardware that comprise or that be associated with equipment 200 or software angle.For example, each endorses same Packet engine of operation or VIP code or configuration still at the different enterprising line operates of distributed data collection.Each network hardware or software configuration can receive different, data that change or basic identical amount, thereby can have variation, different or the load 515 of same amount relatively.

Under the situation of data parallel method, can divide and distribution work based on the data stream of VIP, NIC and/or VIP or NIC.In these of method, can the work of multiple nucleus system be divided or is distributed among the VIP through each VIP is worked on the data set that distributes.For example, the one or more VIP of configurable each nuclear operation.Network can be distributed on the nuclear of each VIP that manages business.In another of these methods, can receive Network based on which NIC the work of equipment is divided or is distributed on the nuclear.For example, the Network of a NIC can be distributed to first nuclear, and the Network of the 2nd NIC simultaneously can be distributed to second nuclear.Under the certain situation, endorse the data of processing from a plurality of NIC.

Though Fig. 5 A shows the single vServer that is associated with single nuclear 505, as the situation of VIP1 275A, VIP2 275B and VIP3 275C.But among some embodiment, single vServer can examine 505 with one or more and be associated.On the contrary, one or more vServer can be associated with single nuclear 505.VServer is handled and the related all functions of this specific vServer with nuclear 505 related these nuclears 505 that comprise.Among some embodiment, each nuclear is carried out the VIP with same code and configuration.Among other embodiment, each nuclear execution has same code but disposes different VIP.Among some embodiment, each nuclear is carried out the VIP with different code and identical or different configuration.

Similar with vServer, NIC also can be related with specific nuclear 505.Among many embodiment, NIC can be connected to one or more nuclears 505, and like this, when NIC reception or transmission of data packets, specific nuclear 505 is handled the processing that relates to reception and transmission of data packets.Among the embodiment, single NIC can be associated with single nuclear 505, as the situation of NIC1 542D and NIC2 542E.Among other embodiment, one or more NIC can be associated with single nuclear 505.But among other embodiment, single NIC can examine 505 with one or more and be associated.Among these embodiment, load can be distributed on one or more nuclears 505, makes each nuclear 505 handle similar charge capacity basically.The nuclear 505 related with NIC can be handled and related all functions and/or the data of this specific NIC.

Though the data according to VIP or NIC are distributed in the independence that has on the nuclear to a certain degree with work,, among some embodiment, this can cause the unbalanced use of the nuclear shown in the varying duty 515 of Fig. 5 A.

Among some embodiment, can load, work or Network be distributed on the nuclear 505 according to the data stream of any kind or form.In another of these methods, can will work based on data stream and divide or be distributed on a plurality of nuclears.For example, between client computer or the server through the Network of equipment can be distributed in a plurality of nuclears nuclear and by its processing.Under the certain situation, set up the nuclear that Network was distributed of endorsing of session or connection at first to be this session or connection.Among some embodiment, any unit or the part of data stream business Network Based are like affairs, request communication or from the business of the application on the client computer.Like this, among some embodiment, between the client-server through the data stream of equipment 200 ' can than other modes distribute more balanced.

In the data parallel mechanism 520 based on stream, the data stream of DATA DISTRIBUTION and any kind is relevant, and for example request is to, affairs, session, connection or application communication.For example, between client computer or the server through the Network of equipment can be distributed in a plurality of nuclears nuclear and by its processing.Under the certain situation, set up the nuclear that Network was distributed of endorsing of session or connection at first to be this session or connection.The distribution of data stream can be so that each nuclear 505 operation basic equal or equally distributed relatively charge capacity, data volume or network traffic.

Among some embodiment, any unit or the part of data stream business Network Based are like affairs, request communication or be derived from the business of the application on the client computer.Like this, among some embodiment, between the client-server through the data stream of equipment 200 ' can than other modes distribute more balanced.Among the embodiment, can be based on affairs or a series of affairs distributed data amount.Among some embodiment, these affairs can be between the client-server, and its characteristic can be IP address or other packet identifiers.For example, examine 1 505A and can be exclusively used in the affairs between specific client and the particular server, therefore, examine load 536A on 1 505A can comprise with specific client and server between the Network that is associated of affairs.Can be routed to nuclear 1 505A through all packets that will be derived from specific client or server nuclear 1 505A is distributed in Network.

Affairs will be worked or load distribution arrives nuclear though can be based in part on,, among other embodiment, can distribute load or work based on the basis of each grouping.Among these embodiment, but equipment 200 data interception are divided into groups and the minimum nuclear 505 of charge capacity is distributed in packet.For example, because the load 536A on the nuclear 1 is less than the load 536B-N on other nuclear 505B-N, so equipment 200 can be distributed to nuclear 1 505A with the packet of first arrival.After first packet distributed to nuclear 1 505A, examine on 1 505A charge capacity 536A with handle the required proportional increase of processing stock number of first packet.When equipment 200 was intercepted second packet, equipment 200 can give nuclear 4 505D load allocating, and this is because nuclear 4 505D have the second few charge capacity.Among some embodiment, minimum the endorsing of charge capacity distributed in packet guaranteed that the load 536A-N that is distributed to each nuclear 505 keeps equal basically.

Among other embodiment, a part of Network being distributed under the situation of particular core 505, can every unit be that load is distributed on the basis.Above-mentioned example description carries out load balance whenever to be grouped into the basis.Among other embodiment, can distribute load, for example, give the minimum nuclear 505 of portfolio per 10,100 or 1000 packet allocation based on grouping number.Distributing to nuclear 505 number of packet can be the number of being confirmed by application, user or keeper, and can be for greater than any number of zero.Still in other embodiments, distribute load, make that section is distributed to particular core 505 with grouping at the fixed time based on time index.Among these embodiment, can in 5 milliseconds or by the definite any time section of user, program, system, manager or other modes, grouping be distributed to particular core 505.Predetermined amount of time is transferred to different nuclear 505 with time packet in the section after the past at the fixed time.

Be used for the data parallel method based on stream that work, load or Network are distributed on one or more nuclears 505 can be comprised the combination in any of the foregoing description.These methods can be carried out by any part of equipment 200, carry out by the application of on nuclear 505, carrying out or one group of executable instruction, Packet engine for example, perhaps by with calculation element that equipment 200 communicate by letter on any application, program or the agency's execution carried out.

Function shown in Fig. 5 A and data parallel mechanism numerical procedure can make up by any way; Producing hybrid parallel mechanism or distributed treatment scheme, it comprises function parallelization mechanism 500, data parallel mechanism 540, based on data parallel mechanism 520 or its any part of stream.Under the certain situation, the load balance scheme that multiple nucleus system can use any kind or form with load distribution on one or more nuclears 505.The load balance scheme can be used with any function and data parallel scheme or its incorporate.

Fig. 5 B illustrates the embodiment of multiple nucleus system 545, and this system can be one or more systems, unit or the assembly of any kind or form.Among some embodiment, this system 545 can be included in the equipment 200 with one or more process nuclear 505A-N.System 545 also can comprise one or more Packet engine (PE) or packet processing engine (PPE) 548A-N that communicates by letter with memory bus 556.Memory bus can be used for communicating by letter with one or more process nuclear 505A-N.System 545 also can comprise one or more NICs (NIC) 552 and distributions device 550, and the distributions device also can be communicated by letter with one or more process nuclear 505A-N.Distributions device 550 can comprise receiver side adjuster (Receiver Side Scaler-RSS) or receiver side adjustment (Receiver Side Scaling-RSS) module 560.

Further with reference to figure 5B, particularly, among the embodiment, Packet engine 548A-N can comprise any part of equipment described herein 200, for example any part of Fig. 2 A and the said equipment of 2B.Among some embodiment, Packet engine 548A-N can comprise any following element: Packet engine 240, network stack 267, cache manger 232, policy engine 236, compression engine 238, crypto engine 234, GUI 210, CLI 212, shell service 214, watchdog routine 216 and can be from data bus 556 or one or more nuclear 505A-N any receive other any software and hardware elements of packet.Among some embodiment, Packet engine 548A-N can comprise one or more vServer 275A-N or its any part.Among other embodiment, Packet engine 548A-N can provide the combination in any of following function: SSL VPN 280, in-house network IP 282, exchange 284, DNS 286, divide into groups to quicken 288, APP FW 280, as the monitoring that provides by monitoring agent 197 be connected as TCP storehouse related function, load balance, SSL unloading and processing, content exchange, Policy evaluation, high-speed cache, compression, coding, decompression, decoding, application firewall function, XML processing and acceleration and SSL VPN.

Among some embodiment, Packet engine 548A-N can with particular server, user, client or network associate.When Packet engine 548 was related with special entity, Packet engine 548 can be handled the packet with this entity associated.For example, if Packet engine 548 is related with first user, this Packet engine 548 will be handled and operate the grouping or the destination address grouping related with first user that are produced by first user so.Similarly, Packet engine 548 can be selected not related with special entity, make Packet engine 548 can be not produce by this entity or purpose be that any packet of this entity is handled and otherwise operated.

In some instances, can Packet engine 548A-N be configured to any function shown in the execution graph 5A and/or data parallel scheme.In these instances, Packet engine 548A-N can be with function or DATA DISTRIBUTION on a plurality of nuclear 505A-N, thereby make and distribute according to parallel mechanism or distribution scheme.Among some embodiment, single Packet engine 548A-N carries out the load balance scheme, and among other embodiment, one or more Packet engine 548A-N carry out the load balance scheme.Among the embodiment, each nuclear 505A-N can be related with specific cluster engine 505, makes and can carry out load balance by Packet engine 505.In this embodiment, load balance can require and examine 505 related each Packet engine 505 and communicate by letter with nuclear 505 other related Packet engine 505, makes Packet engine 505 to determine with load distribution wherein jointly.An embodiment of this process can comprise the moderator that receives for the ballot of load from each Packet engine 505.Moderator can be based in part on the duration of engine ballot and give each Packet engine 505 with load allocating; Under the certain situation, also can be based on giving each Packet engine 505 with load allocating with the priority value that present load amount on the related nuclear 505 of engine is associated.

Any Packet engine of operation can run on user model, kernel mode or its combination in any on the nuclear.Among some embodiment, Packet engine is operated as application or the program in user's space or application space, moved.Among these embodiment, Packet engine can use the interface of any kind or form to visit any function that kernel provides.Among some embodiment, Packet engine operates in the kernel mode or as the part of kernel and operates.Among some embodiment, the first of Packet engine operates in the user model, and the second portion of Packet engine operates in the kernel mode.Among some embodiment, first Packet engine on first nuclear is executed in the kernel mode, and simultaneously, second Packet engine on second nuclear is executed in the user model.Among some embodiment, Packet engine or its any part NIC or its any driver are operated or with its joint operation.

Among some embodiment, memory bus 556 can be the storer or the computer bus of any kind or form.Though in Fig. 5 B, described single memory bus 556, system 545 can comprise the memory bus 556 of any amount.Among the embodiment, each Packet engine 548 can be associated with one or more independent memory bus 556.

Among some embodiment, NIC 552 can be any NIC or a mechanism described herein.NIC552 can have the port of any amount.NIC can design and be configured to be connected to the network 104 of any kind and form.Though single NIC 552 is shown,, system 545 can comprise the NIC 552 of any amount.Among some embodiment, each nuclear 505A-N can be related with one or more single NIC 552.Thereby each nuclear 505 can be related with the single NIC 552 that is exclusively used in particular core 505.Nuclear 505A-N can comprise any processor described herein.In addition, can dispose nuclear 505A-N according to any nuclear described herein 505.In addition, nuclear 505A-N can have any nuclear 505 functions described herein.Though Fig. 5 B illustrates seven nuclear 505A-G, system 545 can comprise the nuclear 505 of any amount.Particularly, system 545 can comprise N nuclear, and wherein N is the integer greater than zero.

Endorse to have or use and be assigned with or assign the storer that is used for this nuclear.Can storer be regarded as the proprietary or local storage of this nuclear and only have this to endorse this storer of visit.Endorse have or use share or assign the storer of giving a plurality of nuclears.This storer can be regarded as by not only public or shared storage of endorsing visit.Endorse any combination of using proprietary or common storage.Through the separate addresses space of each nuclear, some that eliminated under the situation of using same address space are coordinated rank.Utilize the separate addresses space, endorse so that information in the address space of examining oneself and data are carried out work, and do not worry and other nuclear conflicts.Each Packet engine can have the single memory pond that is used for TCP and/or SSL connection.

Still with reference to figure 5B, among any embodiment of the virtualized environment that any function of the nuclear 505 of preceding text combination Fig. 5 A description and/or embodiment can be deployed in preceding text combination Fig. 4 A and 4B description.Be not the function of disposing nuclear 505 with the form of concurrent physical processor 505, but with these function distributings in virtualized environment 400 such as any calculation element 100 of client computer 102, server 106 or equipment 200.Among other embodiment, be not the function of disposing nuclear 505 with the form of an equipment or a device, but with this function distributing on the multiple arrangement of any layout.For example, a device can comprise two or more nuclears, and another device can comprise two or more nuclears.For example, multiple nucleus system can comprise the network of cluster, server zone or the calculation element of calculation element.Among some embodiment, be not the function of disposing nuclear 505 with the form of nuclear, but with this function distributing on a plurality of processors, for example dispose on a plurality of single core processor.

Among the embodiment, nuclear 505 can be the processor of any form or type.Among some embodiment, the function of nuclear can similar basically any processor or CPU described herein.Among some embodiment, nuclear 505 can comprise any part of any processor described herein.Though Fig. 5 A illustrates 7 nuclears,, in the equipment 200 any N nuclear can be arranged, wherein N is the integer greater than 1.Among some embodiment, nuclear 505 can be installed in the shared device 200, and among other embodiment, nuclear 505 can be installed in the one or more equipment 200 that connect that communicate with one another.Among some embodiment, nuclear 505 comprises PaintShop, and among other embodiment, nuclear 505 provides the general procedure ability.The nuclear 505 physics connection of closely installing and/or can communicate with one another each other.Can be coupled to any kind of nuclear and the bus or the subsystem of form is connected nuclear in order to physics mode and/or communication mode, be used for to nuclear, transmit data from nuclear and/or between nuclear.

Each nuclear 505 can comprise and be used for examining the software of communicating by letter with other that among some embodiment, nuclear manager (not shown) can help the communication between each nuclear 505.Among some embodiment, in endorse nuclear management be provided.Endorse to use interface or the communication each other of various interface mechanism.Among some embodiment, can use the message of nuclear to send communication between nuclear, authorize to second such as, first nuclear bus or the subsystem through being connected to nuclear and send message or data.Among some embodiment, endorse shared storage interface communication through any kind of or form.Among the embodiment, can exist in one or more memory cells of sharing in all nuclears.Among some embodiment, each is endorsed to have the single memory unit that other nuclears are shared with each.For example, first endorse have with second nuclear first shared storage, and with the 3rd nuclear second shared storage.Among some embodiment, the programming or the API (like the function call through kernel) that endorse through any kind communicate by letter.Among some embodiment, the multinuclear device can discerned and support to operating system, and be provided for the interface and the API of internuclear communication.

Distributions device 550 can be the executable instruction of any application, program, storehouse, script, task, service, process or any kind of on the hardware of any kind or form, carrying out and form.Among some embodiment, distributions device 550 can be any circuit design or the structure that is used to carry out any operation described herein and function.Among some embodiment, the distribution of distributions device, forwarding, route, control and/or manage data and/or Packet engine or the distribution of VIP of operation on nuclear on a plurality of nuclears 505.Among some embodiment, can distributions device 550 be called interface master device (interface master).Among the embodiment, distributions device 550 is included in one group of executable instruction carrying out on nuclear or the processor of equipment 200.Among another embodiment, distributions device 550 is included in one group of executable instruction carrying out on the computing machine of communicating by letter with equipment 200.Among some embodiment, the NIC that distributions device 550 is included in like firmware goes up one group of executable instruction carrying out.Other embodiment, distributions device 550 comprise any combination that is used for packet is distributed in the software and hardware on nuclear or the processor.Among the embodiment, distributions device 550 is carried out at least one nuclear 505A-N, and in other embodiments, distributes to the independent distributions device 550 of each nuclear 505A-N and on the nuclear 505A-N that is associated, carry out.The distributions device can use the statistics or the probabilistic algorithm of any kind and form or make a strategic decision the stream on a plurality of nuclears of balance.Can be with like device hardware or the core design of NIC or be configured to support the sequential operation on NIC and/or the nuclear.

System 545 comprises among the embodiment of one or more distributions devices 550 that each distributions device 550 can be related with processor 505 or Packet engine 548.Distributions device 550 can comprise the interface mechanism that allows each distributions device 550 to communicate by letter with other distributions devices 550 of in system 545, carrying out.In the instance, how one or more distributions devices 550 can confirm balanced load through communicating with one another.The operation of this process can be basically and said process similar, be about to ballot and submit to moderator, moderator confirms that which distributions device 550 should receive load then.Among other embodiment, first-class distributor 550 ' can discern on the related nuclear load and based on any standards determine whether with first packet be transmitted to related nuclear: the load on the related nuclear greater than predetermined threshold; The load on the related nuclear less than predetermined threshold; The load on the related nuclear less than the load on other nuclears; Perhaps can be used for part confirms packet is forwarded to any other index where based on the charge capacity on the processor.

Distributions device 550 can be distributed in Network on the nuclear 505 according to the described distribution in place like this, calculating or balancing method of loads.Among the embodiment, the distributions device can be based on function parallelization mechanism distribution scheme 550, data parallel mechanism load distribution scheme 540, based on the combination in any of the data parallel mechanism distribution scheme 520 of stream or these distribution schemes or be used for coming distributed network professional any load balance scheme of load distribution on a plurality of processors.Thereby distributions device 550 can serve as the load distribution device through receiving packet and according to the load balance of operation or distribution scheme packet being distributed on the processor.Among the embodiment, distributions device 550 can comprise and how correspondingly to be used for confirming one or more operations, function or the logic of distribute packets, work or load.Among another embodiment, distributions device 550 can comprise can discern the source address related with packet and destination address and correspondingly one or more child-operations, function or the logic of distribute packets.

Among some embodiment, distributions device 550 can comprise receiver side adjustment (RSS) network drive module 560 or packet is distributed in any kind and the executable instruction of form on one or more nuclears 505.RSS module 560 can comprise the combination in any of hardware and software.Among some embodiment,

RSS module

560 and 550 collaborative works of distributions device are to be distributed in packet on a plurality of processors in nuclear 505A-N or the multiprocessor network.Among some embodiment, RSS module 560 can be carried out in NIC 552, among other embodiment, can nuclear 505 any one on carry out.

Among some embodiment, RSS module 560 is used Microsoft's receiver side adjustment (RSS) method.Among the embodiment; RSS is Microsoft's a scalable network active technique (Microsoft Scalable Networking initative technology); It makes reception on a plurality of processors in the system handle is balance, keeps the order of data to transmit simultaneously.RSS can use the Hash scheme of any kind or form to confirm to be used to handle the nuclear or the processor of network packet.

RSS module 560 can be used the hash function of any kind or form, like the Toeplitz hash function.Hash function may be used on Hash types value or any value sequence.Hash function can be the secure hash of any level of security or otherwise encrypt.Hash function can use hash key (hash key).The size of key word depends on hash function.For the Toeplitz Hash, the hash key size that is used for IPv6 is 40 bytes, and the hash key size that is used for IPv4 is 16 bytes.

Can be based on any one or a plurality of standard or design object design or structure hash function.Among some embodiment, can be used for different Hash is imported provides equally distributed hash result with different Hash types hash function, said different Hash inputs comprise TCP/IPv4, TCP/IPv6, IPv4 and IPv6 head with different Hash types.Among some embodiment, can use (for example 2 or 4) when having a small amount of bucket that the hash function of equally distributed hash result is provided.Among some embodiment, can use (for example 64 buckets) when having big measuring tank that the hash function of the hash result of stochastic distribution is provided.In certain embodiments, confirm hash function based on calculating or resource usage level.In certain embodiments, be based on the difficulty that realizes Hash in the hardware and confirm hash function.In certain embodiments, send the difficulty that will all be hashing onto the grouping in the same bucket based on distance host and confirm hash function with malice.

RSS can produce Hash from the input of any type and form, for example value sequence.This value sequence can comprise any part of network packet, like any head, territory or load or its part of network packet.Among some embodiment; Can the Hash input be called the Hash type; Hash input can comprise any information tuple with network packet or data stream association, the type below for example: comprise the four-tuple of at least two IP addresses and two ports, the four-tuple, hexa-atomic group, doublet that comprise any four class values and/or any other numeral or value sequence.Below be the Hash examples of types that can use by RSS:

The four-tuple of-source tcp port, IPv4 address, source, target tcp port and Target IP v4 address.This is the unique essential Hash type that will support.

The four-tuple of-source tcp port, source IP version 6 (IPv6) address, target tcp port and Target IP v6 address.

The doublet of IPv4 address ,-source and Target IP v4 address.

The doublet of IPv6 address ,-source and Target IP v6 address.

The doublet of IPv6 address ,-source and Target IP v6 address comprises resolving the support of IPv6 extended head.

Hash result or its any part can be used for discerning nuclear or the entity that is used for the distributed network grouping, like Packet engine or VIP.Among some embodiment, can use one or more Hash position or mask to hash result.Hash position or mask can be any figure place or byte number.NIC can support any position, for example 7.Network stack can be set the actual number of bits that will use when initialization.Figure place comprises end value between 1 and 7.

Can discern nuclear or entity with hash result through the table of any type and form, for example through bucket table (bucket table) or indirection table (indrection table).Among some embodiment, come concordance list with the figure place of hash result.The scope of Hash mask can limit the size of indirection table effectively.Any part of hash result or hash result self can be used for the index indirection table.Value in the table can identify any nuclear or processor, for example identifies through nuclear or processor identifiers.Among some embodiment, all nuclears of sign multiple nucleus system in the table.Among other embodiment, the part nuclear of sign multiple nucleus system in the table.Indirection table can comprise any a plurality of bucket, and for example 2 to 128 buckets can be used these buckets of Hash mask index.Each barrel can comprise the index value scope of sign nuclear or processor.Among some embodiment, stream controller and/or RSS module can be come balancing network load again through changing indirection table.

Among some embodiment, multiple nucleus system 575 does not comprise RSS driver or RSS module 560.In some of these embodiment; The software implementation example of RSS module can be operated with distributions device 550 co-operate or as the part of distributions device 550 in software operational module (not shown) or the system, so that grouping is directed to the nuclear 505 in the multiple nucleus system 575.

On any module or program in carry out, carry out on any one nuclear 505 that perhaps in multiple nucleus system 575, comprises and arbitrary device or the assembly.Among some embodiment, distributions device 550 ' can be carried out on the first nuclear 505A, and in other embodiments, distributions device 550 " can on NIC 552, carry out.Among other embodiment, carry out on each nuclear 505 that the instance of distributions device 550 ' can comprise in multiple nucleus system 575.Among this embodiment, each instance of distributions device 550 ' can and other instance communications of distributions device 550 ' divide into groups between nuclear 505, to transmit back and forth.Have such situation, wherein, the request response packet is not handled by same nuclear, promptly first nuclear is handled request, and the second nuclear processing response.Under these situation, the instance of distributions device 550 ' can interception packet and is given expectation or correct nuclear 505 with packet forward, and promptly distributions device 550 ' can be transmitted to first nuclear with response.A plurality of instances of distributions device 550 ' can or be examined in any combination of 505 and carry out at the nuclear 505 of any amount.

The distributions device can be operated in response to any or a plurality of rule or strategy.Rule can be discerned nuclear or the packet processing engine that receives network packet, data or data stream.Rule can be discerned any kind relevant with network packet and the tuple information of form, for example the four-tuple of source and target IP address and source and target port.Based on the grouping of the specified tuple of the matched rule that is received, the distributions device can be given nuclear or Packet engine with packet forward.Among some embodiment, give nuclear with packet forward through the transmission of messages of shared storage and/or nuclear.

Though Fig. 5 B shows the distributions device of in multiple nucleus system 575, carrying out 550,, among some embodiment, distributions device 550 can be carried out on the calculation element or equipment that are positioned at away from multiple nucleus system 575.Among such embodiment, distributions device 550 can be communicated by letter with multiple nucleus system 575 to receive packet and grouping is distributed on one or more nuclears 505.Among the embodiment, it is the packet of purpose that distributions device 550 receives with equipment 200, is distributed to one or more nuclears 505 of multiple nucleus system 575 to the packet application distribution scheme that is received and with packet.Among the embodiment; Distributions device 550 can be included in router or other equipment; Router can be a target through changing with the metadata of each packet associated with particular core 505 like this, thereby each child node of dividing into groups with multiple nucleus system 575 is a target.Among such embodiment, each grouping that the vn-tag mechanism of available CISCO changes or mark has appropriate metadata.

Fig. 5 C illustrates the embodiment of the multiple nucleus system 575 that comprises one or more process nuclear 505A-N.In brief, in the nuclear 505 can be designated as control nuclear 505A and can be used as other and examine 505 control plane 570.Other are endorsed to be secondary nuclear, and it works in datum plane, and control nuclear provides control plane.Nuclear 505A-N shares overall high-speed cache 580.Control nuclear provides control plane, and other karyomorphisms in the multiple nucleus system become or datum plane is provided.These are checked Network and carry out data processing function, and control nuclear provides initialization, configuration and the control to multiple nucleus system.

Still with reference to figure 5C, particularly, nuclear 505A-N and control nuclear 505A can be any processors described herein.In addition, nuclear 505A-N can be any processor that can in the said system of Fig. 5 C, work with control nuclear 505A.In addition, nuclear 505A-N can be any nuclear or a nuclear group described herein.Control is endorsed to be nuclear or the processor dissimilar with other nuclears.Among some embodiment, control is endorsed operation different packets engine or is had the Packet engine configuration different packets engine with other nuclears.

Any part of the storer of each nuclear can be assigned to or be used as the overall high-speed cache that nuclear is shared.In brief, the predetermined percentage of each storer of each nuclear or scheduled volume can be used as overall high-speed cache.For example, 50% of each storer of each nuclear can be used as or distributes to and share overall high-speed cache.That is to say, in the illustrated embodiment, except control plane nuclear or the 2GB that examines each nuclear 1 can be used for forming the shared overall high-speed cache of 28GB.For example dispose the memory space (the amountof memeory) that control plane can confirm to be used for sharing overall high-speed cache through configuration service.Among some embodiment, each is endorsed the memory space that provides different and supplies overall high-speed cache to use.Among other embodiment, arbitrary endorsing any storer not to be provided or not to use overall high-speed cache.Among some embodiment, any nuclear also can have the unallocated local cache of giving in the storer of overall shared storage.Each arbitrary portion of endorsing Network is stored in the overall shared cache.Each is endorsed the inspection high-speed cache and searches any content that will in request or response, use.Any endorsing from overall shared cache obtains content data stream, request or response, to use.

Overall situation high-speed cache 580 can be the storer or the memory element of any type or form, any storer or memory element for example described herein.Among some embodiment, examine 505 addressable predetermined memory spaces (being 32GB or any other memory space suitable) with system 575.Overall situation high-speed cache 580 can distribute from predetermined memory space, and simultaneously, remaining available memory can distribute between nuclear 505.Among other embodiment, each nuclear 505 can have predetermined memory space.Overall situation high-speed cache 580 can comprise the memory space of distributing to each nuclear 505.This memory space can byte be that unit is measured, and perhaps available allocation is recently measured to the storer percentage of each nuclear 505.Thereby, overall high-speed cache 580 can comprise from the 1GB storer of each nuclear 505 related storer, perhaps can comprise the storer related with each nuclear 505 20% or half.Some embodiment, only some nuclear 505 provides storer to overall high-speed cache 580, and at other embodiment, overall high-speed cache 580 can comprise the unallocated storer of giving nuclear 505.

Each nuclear 505 can use overall high-speed cache 580 to come storage networking professional or data cached.Among some embodiment, the Packet engine of nuclear is used overall high-speed cache to come buffer memory and is used the data of being stored by a plurality of Packet engine.For example, the caching function of the cache manger of Fig. 2 A and Fig. 2 B can use overall high-speed cache to come shared data to be used for acceleration.For example, each Packet engine can be stored the for example response of html data in overall high-speed cache.The addressable overall high-speed cache of any cache manger that operates on the nuclear offers client requests with the high-speed cache response.

Among some embodiment, nuclear 505 can use overall high-speed cache 580 to come the storage port allocation table, and it can be used for part and flows based on the port specified data.Among other embodiment, examine 505 and can use overall high-speed cache 580 to come memory address question blank or any other table or tabulation, the distributions device can use these tables to confirm where the packet of arrival and the packet of sending are led.Among some embodiment, nuclear 505 can be read and write high-speed cache 580, and among other embodiment, nuclear 505 is only perhaps only write to high-speed cache from cache read.Endorse and use overall high-speed cache to carry out nuclear communication.

Can overall high-speed cache 580 be divided into each memory portion, wherein each part can be exclusively used in particular core 505.Among the embodiment, control nuclear 505A can receive a large amount of available high-speed caches, and the visit capacity that other nuclears 505 can receive the variation of overall high-speed cache 580.

Among some embodiment, system 575 can comprise control nuclear 505A.Though Fig. 5 C will examine 1 505A and be shown control nuclear,, control is endorsed to be any one nuclear in equipment 200 or the multiple nucleus system.In addition, though single control nuclear has only been described,, system 575 can comprise one or more control nuclears, each control check system has control to a certain degree.Among some embodiment, one or more controls are endorsed with the particular aspects of control system 575 separately.For example, endorse the control decision for one and use which kind of distribution scheme, and another endorses the size of confirming overall high-speed cache 580.

The control plane of multiple nucleus system can be with a nuclear appointment and be configured to special-purpose management core perhaps as main nuclear.Control plane is endorsed provides control, management and coordination to the operation of a plurality of nuclears in the multiple nucleus system and function.Control plane is endorsed provides control, management and coordination to the distribution of accumulator system on a plurality of nuclears in the multiple nucleus system and use, and this comprises initialization and config memory system.Among some embodiment, control plane comprises the distributions device, is used for flowing to the distribution of nuclear and the distribution that network packet arrives nuclear based on the data flow con-trol data.Among some embodiment, control plane nuclear operation Packet engine, among other embodiment, control plane nuclear is exclusively used in the control and the management of other nuclears of system.

Control nuclear 505A can examine 505 to other and carry out certain other control of level, for example, confirms how many memory allocation are examined 505 to each, confirms that perhaps which assign examine handles specific function or hardware/software entity.Among some embodiment, control nuclear 505A can control these nuclears 505 in the control plane 570.Thereby, the processor that can exist uncontrolled nuclear 505A to control outside the control plane 570.The border of confirming control plane 570 can comprise that the agency by execution in control nuclear 505A or the system 575 keeps the tabulation by the nuclear of control nuclear 505A control.Below the control nuclear 505A may command any: nuclear initialization; When unavailable definite kernel is; When a nuclear is out of order load is redistributed to other nuclear 505; Which distribution scheme decision realizes; Determine which nuclear should receive Network; How many high-speed caches decision should distribute to each nuclear; Determine whether specific function or element are distributed to particular core; Determine whether to allow nuclear to communicate with one another; Confirm the size of overall high-speed cache 580 and to the function of the nuclear in the system 575; Any other of configuration or operation confirmed.

F. In multiple nucleus system, use the system and method for distributed hashtable

The system and method that describes below is in multiple nucleus system 545, using distributed hashtable 600.Generally speaking, distributed hashtable 600 can be used for following the tracks of the use of the resource on a plurality of nuclears 505 in multiple nucleus system 545 and/or keeps said Resources Sustainability.Each nuclear 505 can comprise the copy of distributed hashtable 600, or in other embodiments, can accessing individual distributed hashtable 600.Distributed hashtable 600 can be divided into a plurality of subregions.Each subregion can be assigned to different nuclear 505, or have by different nuclear 505.For example, each subregion can be to be kept by the explorer (not shown) of packet processing engine on the nuclear that has this subregion 505 548 or packet processing engine 548.Each subregion can be associated with one or more resources.Have subregion like fruit stone 505, the packet processing engine 548 on this nuclear 505 can be set up resource in this subregion.Do not have subregion like fruit stone 505, then this nuclear 505 must ask owner's nuclear to set up resource.Packet processing engine on owner's nuclear is set up this resource and this resource information is sent to the requestor and examines 505 in the subregion of its distributed hashtable 600.The packet processing engine that the requestor examines on 505 is examined this information cache in the subregion of distributing to this owner's nuclear of 505 forms kept this requestor.In addition, the packet processing engine of nuclear on 505 can upgrade the resource in the subregion that nuclear 505 has, and examine 505 can ask and buffer memory to the renewal of the resource in the subregion of distributing to other nuclears 505.

Refer now to Fig. 6 A, described the block diagram of the distributed hashtable 600 that comprises a plurality of subregions.Distributed hashtable 600 (also can be called partition table sometimes) can be shared by a plurality of nuclears on the multiple nucleus system 545 505.This table 600 can be in shared storage, perhaps each nuclear 505 copy that its this table of keeping can be arranged (for example table 600 ', table 600 ", to showing N ").Table such as nuclear 1 table 600 can comprise a plurality of subregion 601a-n.Each subregion 601a-n can be assigned to different nuclear 505 in the table 600, is perhaps had by different nuclear 505.In this embodiment, nuclear 1 can have subregion 601a, nuclear 2 can have subregion 601b, and the like.The information of nuclear 1 can created and store to nuclear 1 in subregion 601a.Nuclear 1 can receive other nuclear information of 505 and with this information cache in subregion corresponding to nuclear 505.In one example, nuclear 1 can receive the information of nuclear 2 and it is buffered among the subregion 601b.In another example, nuclear 1 can receive the information of nuclear N and it is buffered among the subregion 601n.Likewise, nuclear 2 table 600 ' can comprise a plurality of subregion 601a-n ', and subregion 601a-n ' can have by different nuclear 505, perhaps with the table 600 of nuclear 1 in the similar mode of the subregion 601a-n information of storing nuclear 505.For any table in the distributed hashtable, section post is had the right and the storage of information can be carried out similarly.

Nuclear 505 can will stored information through using Hash to the information requested of the resource Hash of transport layer link information (for example, to) to confirm which nuclear has.This Hash can be as the index in the distributed hashtable 600.For example, in certain embodiments, can drop in the predetermined value scope any Hash of information requested.Can the preset range of value be divided into a plurality of subranges according to the quantity of multiple nucleus system 545 cokers 505.Therefore, if in first subrange to Hash value of dropping on of information requested, then first nuclear has requested resource.If in second subrange of Hash value of dropping on of information, then second nuclear has requested resource, and the rest may be inferred.In each embodiment, have requested resource like fruit stone 505, then this resource can set up or upgrade to this nuclear 505 in the subregion of distributing to this nuclear 505.In other embodiments, do not have requested resource like fruit stone 505, then this nuclear 505 can be authorized to refer to and ask to set up or new resources more to the owner.Owner's nuclear is set up in its subregion or is upgraded this resource and resource information is sent to the requestor and examine 505.The requestor examines 505 this resource information is buffered in the subregion of distributing to this owner nuclear in its form of keeping.

Nuclear 505 information can comprise, for example, and by the relevant any kind of resource this nuclear identification, management or foundation or that otherwise have and the information of form.For example, can the resource of being set up by nuclear 505 be stored in the subregion of distributing to this nuclear 505.This information can comprise any information that is used for tracking assets, for example identifier and/or title.This information can comprise any time information relevant with resource, time of for example creating and last time of using.This information can comprise any information relevant with state of resources or situation.This information can comprise and the affairs of resource or the historical relevant any information of use of resource.

Resource via distributed hashtable 600 management can comprise any resource of being discerned, managing or being controlled by multiple nucleus system 545 or its any part.In certain embodiments, resource can comprise session.In other embodiments, resource can be included in the connection of service.In more embodiment, resource can comprise the watch-dog that is used to serve.In a plurality of embodiment, resource can comprise safety certificate.In certain embodiments, resource can be cookie.In other embodiments, resource can be an identifier server.In certain embodiments, resource can be URL.In certain embodiments, resource can be the content of buffer memory.In certain embodiments, resource can be the user.In other embodiments, resource can be any service, function or the operation that is provided by Packet engine.

Refer now to Fig. 6 B, show and described the process flow diagram of step of the embodiment of the method for describing to be used on a plurality of nuclears of multiple nucleus system, to keep resource continuous property.Generally speaking, this method comprises the request that is received (step 611) recognition resource by nuclear 505.This method comprises that also definite (step 613) will store the nuclear 505 of this resource.To store this resource if receive the nuclear 505 of this request, then this method is also included within and sets up in the subregion of distributing to this nuclear 505 or renewal (step 615) this resource.Can not store this resource if receive the nuclear 505 of this request, then this method comprises that also examining 505 to the owner sends the request that this resource was set up or upgraded to (step 617).This method comprises that also reception (step 619) examines 505 resource information from the owner.This method is also included within to be distributed to the owner and examines this resource information of buffer memory (step 621) in 505 the subregion.

Nuclear 505 can receive the request of recognition resource from distributions device 550.Distributions device 550 can be according to combining the described any method of Fig. 5 B that request is distributed to nuclear 505.In certain embodiments, the packet processing engine on the nuclear 505 548 receives and should ask.In each embodiment, packet processing engine 548 receives this request being configured to provide on the virtual server of resource continuous property.

Multiple nucleus system 545 can be confirmed the nuclear 505 of storage resources according to the algorithm of any kind and form or decision-making.In certain embodiments, packet processing engine 548 can generate the Hash to the transport layer link information of request.Packet processing engine 548 can be confirmed the nuclear of storage resources based on this Hash.For example, if this Hash drops in first subrange that combines the described value of Fig. 6 A, then packet processing engine 548 can be confirmed the first nuclear storage resources.If in second subrange of this Hash value of dropping on, then packet processing engine 548 can be confirmed the second nuclear storage resources, and the like.In certain embodiments, packet processing engine 548 can be confirmed nuclear 505 storage resources corresponding to this packet processing engine 548.In other embodiments, packet processing engine 548 can confirm that another nuclear is with storage resources.In a plurality of embodiment, packet processing engine 548 can be confirmed the nuclear of storage resources through the subregion that the nuclear of this engine is distributed in visit.In certain embodiments, multiple nucleus system 545 can use storage resources and the related question blank (not shown) of examining between 505.

If the nuclear 505 that receives this request, examines then that packet processing engine 548 on 505 can be set up also with storage resources in the subregion of distributing to this nuclear 505 or new resources more.Packet processing engine 548 addressable these subregions are to confirm whether resource has been stored in this subregion.If resource is not stored as yet, then packet processing engine 548 can be set up this resource in this subregion.If resource is stored, then packet processing engine 548 can upgrade this resource.In certain embodiments, after the resource in regeneration block, packet processing engine 548 can to before buffer memory send the message that has through the resource information of upgrading about other nuclears 505 of the information of this resource.

If the nuclear 505 that receives this request is storage resources not, then examine 505 packet processing engine 548 and can authorize to send to the owner and set up or the more request of new resources.Nuclear 505 can check whether the subregion of its Hash table related with the owner is stored with definite resource.If resource is not stored as yet, then examines 505 packet processing engine 548 and can authorize the request of setting up resource of sending to the owner.If resource is stored, then examines 505 packet processing engine 548 and can authorize the more request of new resources of sending to the owner.After the resource information of receiving from owner nuclear, the packet processing engine 548 on the nuclear 505 can be distributed to this resource information of buffer memory among the Hash table 600a-n in the subregion of owner's nuclear at it.

Refer now to Fig. 6 C, show and described the process flow diagram of step of the embodiment of the method for describing to be used on a plurality of nuclears of multiple nucleus system, to keep session continuity, wherein said session is based upon in the distributed hashtable.Generally speaking, this method comprises by 548 receptions (step 631) of the packet processing engine on the nuclear 505 request to session.This method also comprises by packet processing engine 548 confirms that there has been session in (step 633) in table 600.This method also comprises the state of being confirmed the service of (step 635) and this session association by packet processing engine 548.If the state of service is " online (up) ", then this method also comprises by packet processing engine provides (step 637) to give the virtual server that is associated with this service this request.If the state of service is " (down) rolls off the production line ", then this method also comprises by packet processing engine 548 and confirms that (step 639) will store the subregion of this session.To store this session if distribute to the subregion of the nuclear of this engine 548, then this method also comprises load balance, upgrades this session, and authorizes to other and to send (step 641) to comprise about the message through the information of the session upgraded.To store this session if distribute to the subregion of different nuclear, then this method also comprises authorizing to the owner and send (step 643) to upgrade the request of this session.This method also comprises from owner's stone grafting receives (step 645) and this information through the session association of renewal.This method is also included within buffer memory (step 647) and this information through the session association of renewal in the subregion of distributing to owner's nuclear.

Refer now to Fig. 6 D, show and described the process flow diagram of step of the embodiment of the method for describing to be used on a plurality of nuclears of multiple nucleus system, to keep session continuity, wherein said session is not based upon in the distributed hashtable.Generally speaking, this method comprises by 548 receptions (step 651) of the packet processing engine on the nuclear 505 request to session.This method also comprises by packet processing engine 548 confirms that there is not session in (step 653) in Hash table.This method also comprises by packet processing engine 548 definite (step 655) will store the subregion of this session.Also be assigned with the subregion that will store this session if receive the nuclear 505 of request, then this method also comprises by packet processing engine 548 establishment (step 657) these sessions and carries out load balance.Be not assigned with the subregion with this session of storage if receive the nuclear 505 of request, then this method comprises being authorized to the owner by packet processing engine 548 and send (step 659) to have the message of the information of creating this session.In certain embodiments, the packet processing engine 548 on the nuclear 505 can keep this request till receiving response.In certain embodiments, packet processing engine 548 can be put into formation with any packet of being received when the wait-for-response.This method also comprises by packet processing engine 548 receptions (step 661) from the information of owner's nuclear and the state of estimation service.If the state of service is " online ", then this method is also included within the information of buffer memory (step 663) and session association in the subregion of distributing to owner nuclear.If the state of service is " rolling off the production line ", then this method turns back to step 659 and send another message that has the information of creating this session to authorize to the owner.

Refer now to Fig. 6 E, show and described the process flow diagram of step of the embodiment of the method for describing to be used to use distributed hashtable to keep resource continuous property, wherein stone grafting is received from the establishment of other nuclears or the more request of new session.This method comprises by 548 receptions (step 671) of the packet processing engine on the nuclear 505 from the establishment of another nuclear or the more request of new session.This method also comprises by packet processing engine 548 confirms that (step 673) distribute to the subregion of nuclear 505 and whether comprise this session.If this subregion comprises this session, then this method also comprises the state of being confirmed (step 675) service by packet processing engine 548.If the state of service is " online (up) ", then this method also comprises being authorized to the requestor by packet processing engine 548 and send (step 677) to have the response of the information of this service.If this subregion does not comprise that the state of this session or service is " rolling off the production line ", this method also comprises by packet processing engine 548 load balances, select new service, create session and authorize to the requestor and send (step 679) to have the response of this session information.

In view of structure, function and the device of system and method described herein, this solution is provided for dynamic, the effective and intelligent system of the distributed hashtable of resource continuous property in multiple nucleus system.Describe some embodiment of the method and system of the monitoring that is used for providing multiple nucleus system, to those skilled in the art, obviously can use other embodiment that comprise notion of the present invention.Therefore, the present invention should be not limited to some embodiment, and should be limited by the spirit and the scope of equivalent structures.

Claims

1. keep the method for the resource information of the resource of being set up by a plurality of Packet engine via distributed table for one kind, carry out on the corresponding nuclear of each Packet engine in multiple nucleus system, said method comprises:

A) set up the table that comprises a plurality of subregions by multiple nucleus system, each subregion of said a plurality of subregions is assigned to the corresponding nuclear of a plurality of nuclears of multinuclear device;

The resource information of the resource that b) will be set up by first Packet engine by first Packet engine of first nuclear of said a plurality of nuclears stores first subregion of said a plurality of subregions into, and will be stored into second subregion of said a plurality of subregions by the resource information that second nuclear is set up by second Packet engine of second nuclear of said a plurality of nuclears;

C) first Packet engine by first nuclear receives the request of discerning first resource; And

D) by first nuclear first Packet engine confirm first resource be stored in the first subregion different partition areas in.

2. method according to claim 1, wherein step (a) also comprises by the multinuclear device and based on the quantity of the nuclear of this multinuclear device said partition table is divided into a plurality of subregions.

3. method according to claim 1, wherein step (c) also comprises by first Packet engine and receives described request being configured to provide on the virtual server of resource continuous property.

4. method according to claim 1, wherein step (c) also comprises by the Hash of first Packet engine generation to the transport layer link information of described request.

5. method according to claim 4, wherein step (d) also comprises by first Packet engine and confirms that based on said Hash first resource is not stored in first subregion.

6. method according to claim 4, wherein step (d) comprises that also discerning first resource by first Packet engine based on said Hash is set up by second nuclear.

7. method according to claim 1, wherein step (d) comprises that also first subregion of visiting said partition table by first Packet engine is to confirm whether first resource is stored in first subregion.

8. method according to claim 1; Also comprise second request that receives identification second resource by first Packet engine; Confirm that second resource is stored in first subregion and the virtual server on first nuclear has online state; And confirm that in response to this second request is offered this virtual server, and wherein first resource is first session and second resource is second session.

9. method according to claim 1; Also comprise second request that receives identification second resource by first Packet engine; Confirm that second resource should be stored in first subregion and is not present in first subregion, and confirm, create second resource in response to this.

10. method according to claim 1 comprises also being authorized to second by first nuclear and send message that this message request information is with establishment first resource on first nuclear.

11. method according to claim 10; Also comprise by second Packet engine and confirm in second subregion of said partition table, to exist first resource; Identification is that the state of the selected service of first resource is online by second Packet engine, and the response that will discern this service sends to first Packet engine.

12. method according to claim 10; Also comprise by second Packet engine and confirm in second subregion of said partition table, not have first resource, and confirm to create first resource, be that the first resource selection service and the response that will discern this service send to first nuclear in response to this.

13. method according to claim 10, also comprise by first stone grafting receive from second nuclear, to the response of said message, confirm that the state of first the above service of nuclear is online, and in first subregion copy of buffer memory first resource.

14. keep the system of the resource information of the resource of setting up by a plurality of Packet engine via distributed partition table for one kind, carry out on the corresponding nuclear of each Packet engine in multiple nucleus system, said system comprises:

By the partition table that multiple nucleus system is set up, said partition table comprises a plurality of subregions, and each subregion is assigned to the corresponding nuclear of said multiple nucleus system;

First Packet engine of on first nuclear of said multiple nucleus system, carrying out; First subregion of the information stores of the resource that it will be set up by first Packet engine in the said partition table; Receive the request of identification first resource; Confirm that first resource is not stored in first subregion, and second subregion of identification storage first resource; With

Second Packet engine of second nuclear of said multiple nucleus system, the information stores of the resource that it will be set up by second Packet engine is to second subregion of said partition table.

15. system according to claim 14, wherein the quantity based on the nuclear of said multiple nucleus system is divided into a plurality of subregions with said partition table.

16. system according to claim 14, wherein first Packet engine receives described request being configured to provide on the virtual server of resource continuous property.

17. system according to claim 14, wherein first Packet engine generates the Hash to the transport layer link information of described request.

18. system according to claim 17, wherein first Packet engine confirms that based on said Hash first resource is not stored in first subregion.

19. system according to claim 17, wherein first Packet engine confirms that based on said Hash first resource is by the second nuclear foundation.

20. system according to claim 14, wherein first Packet engine is visited first subregion to confirm whether first resource is stored in first subregion.

21. system according to claim 14; Wherein first Packet engine receives second request of identification second resource; Confirm that second resource is stored in first subregion and the virtual server on first nuclear has online state; And definite in response to this, second request is offered this virtual server.

22. system according to claim 14; Wherein first Packet engine receives second request of identification second resource; Confirm in first subregion, not exist second resource and second resource should be stored in first subregion, and confirm to create second resource in response to this.

23. system according to claim 14, wherein first nuclear is authorized to second and is sent message, and this message request information is to create first resource on first nuclear.

24. system according to claim 23, wherein second Packet engine is confirmed in second subregion to have first resource, and the state of discern service related with first resource is online, and the response that will discern this service sends to first and examines.

25. system according to claim 23, wherein second Packet engine confirms in second subregion, not exist first resource, in response to said definite establishment first resource, is the first resource selection service, and the response that will discern this service sends to first nuclear.

26. system according to claim 23, wherein first Packet engine receive from second nuclear, to the response of said message, confirm that the state of the service related with first resource is online, and in first subregion copy of buffer memory first resource.